NeuronScope
Traces LLM outputs to the neurons and heads that caused them
What is NeuronScope?
NeuronScope is a CLI and MCP server for mechanistic interpretability. It is built on TransformerLens. Point it at an open-weight model to instantly see which attention heads and neurons drive predictions. Supporting hundreds of checkpoints, it avoids strict allowlists. Its native MCP server and versioned JSON let AI agents (Claude, Cursor) directly trace, ablate, and sketch circuits without any Python coding requirement.
Screenshots
?
No comments yet. Be the first!