© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10922
    Prev
    Next
    INDEX
    Explanations

    the store name "Wal-Mart"

    oai_token-act-pair · gemini-2.0-flash

    Wal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     return
    -0.48
    return
    -0.48
     cou
    -0.46
    writeFieldEnd
    -0.45
     genetic
    -0.44
    moduleName
    -0.44
    imwrite
    -0.41
    peated
    -0.41
    naux
    -0.41
     volta
    -0.40
    POSITIVE LOGITS
     Paglinawan
    0.86
     OFDb
    0.78
     виправивши
    0.72
    󠁢
    0.71
     nahilalakip
    0.69
    abestanden
    0.68
    EDEFAULT
    0.63
    AccessorTable
    0.63
    formatics
    0.62
     للمعارف
    0.62
    Activations Density 0.155%

    No Known Activations