© 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. 13368
    Prev
    Next
    INDEX
    Explanations

    locations like cities, lakes, counties and physical features

    oai_token-act-pair · gemini-2.0-flash

    time and existence

    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
    Negative Logits
     partie
    -0.48
    atnya
    -0.46
    ęg
    -0.46
    <bos>
    -0.44
    cação
    -0.42
     منها
    -0.42
     ch
    -0.41
     Tully
    -0.41
     OnInit
    -0.41
    PMailer
    -0.41
    POSITIVE LOGITS
    QMetaType
    0.77
    IBOutlet
    0.73
     typelib
    0.65
    djangoproject
    0.60
    hirts
    0.57
     cappello
    0.56
    akaian
    0.55
    جغرافيا
    0.55
    ništ
    0.54
     husbands
    0.53
    Activations Density 7.186%

    No Known Activations