© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14930
    Prev
    Next
    INDEX
    Explanations

    mentions of Washington, D.C., and the Washington Post

    oai_token-act-pair · gemini-2.0-flash

    references to Washington

    np_token-act-pair-logits · gpt-4o-mini

    Washington

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    __*/
    -0.63
    ScopeManager
    -0.59
    SharedCtor
    -0.47
     ErrInvalid
    -0.46
    setattr
    -0.46
    /******/
    -0.45
     whereof
    -0.45
    /***/
    -0.44
     sendiri
    -0.44
    addGap
    -0.44
    POSITIVE LOGITS
     National
    0.62
    Архівовано
    0.58
    National
    0.57
     sibuk
    0.56
    WriteAttribute
    0.54
     foli
    0.53
     насељу
    0.53
     NATIONAL
    0.53
     ProtoMessage
    0.53
    ymce
    0.52
    Activations Density 1.264%

    No Known Activations