© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5138
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cap" followed by other letters

    oai_token-act-pair · gemini-2.0-flash

    cap

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    tease
    -0.55
    %");
    -0.51
     Advanced
    -0.51
     sopp
    -0.51
    getRuntime
    -0.50
    AIRE
    -0.50
    />";
    -0.50
     hell
    -0.50
    TypedDataSet
    -0.49
    teady
    -0.49
    POSITIVE LOGITS
     VIAF
    0.66
     مرئيه
    0.60
     StatelessWidget
    0.54
    ftagPool
    0.54
     насеље
    0.52
     odkazy
    0.52
     Benn
    0.50
    !*\
    0.49
     paramInt
    0.49
     hObject
    0.49
    Activations Density 0.655%

    No Known Activations