© 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. 13326
    Prev
    Next
    INDEX
    Explanations

    words or phrases that are authoritative or technical, sometimes even legal or political

    oai_token-act-pair · 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
     GenerationType
    -0.86
     ExecuteAsync
    -0.71
    :✨
    -0.66
    reportWebVitals
    -0.65
    //
    -0.60
     فريبيس
    -0.59
    ✨:
    -0.58
    anueva
    -0.56
    slidesToShow
    -0.56
    enumi
    -0.55
    POSITIVE LOGITS
     cartes
    0.47
    FLP
    0.46
    fag
    0.45
    cellular
    0.45
     chì
    0.44
    ilkan
    0.44
     Keene
    0.44
     extracellular
    0.44
    ніципа
    0.43
    公
    0.43
    Activations Density 21.562%

    No Known Activations