© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9490
    Prev
    Next
    INDEX
    Explanations

    file paths, especially those containing the words "views", "modules", "sites", "shop", and "html"

    oai_token-act-pair · gemini-2.0-flash

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    VersionUID
    -0.46
    UNE
    -0.45
    zzleHttp
    -0.44
     copied
    -0.43
     csal
    -0.43
    ects
    -0.43
     bawat
    -0.43
    ToProps
    -0.43
    出一个
    -0.42
     بیر
    -0.42
    POSITIVE LOGITS
     autorytatywna
    0.85
    MLLoader
    0.79
    Portail
    0.77
     jspb
    0.72
    GEBURTSDATUM
    0.71
     Roskov
    0.70
     ModelRenderer
    0.70
    extAlignment
    0.68
     الرياضيه
    0.66
     '').
    0.66
    Activations Density 4.547%

    No Known Activations