© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 915
    Prev
    Next
    INDEX
    Explanations

    references to introspection and thinking.

    oai_token-act-pair · gemini-2.0-flash

    thought

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -0.74
    TypedDataSet
    -0.69
     Parac
    -0.69
    Spoljašnje
    -0.66
    quilibrium
    -0.64
    Formazione
    -0.63
    raszam
    -0.62
     ***!
    -0.60
     CURIAM
    -0.58
    quiera
    -0.58
    POSITIVE LOGITS
     thought
    1.05
    thought
    0.93
     Thought
    0.92
     THOUGHT
    0.91
     THINK
    0.90
    Thought
    0.86
    THINK
    0.85
     thinking
    0.84
     think
    0.82
     thoughts
    0.79
    Activations Density 0.559%

    No Known Activations