© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15484
    Prev
    Next
    INDEX
    Explanations

    references to previous research or experiments, often appearing with citations and related terminology

    oai_token-act-pair · gemini-2.0-flash

    Research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    IsMutable
    -0.90
     незавершена
    -0.82
     виправивши
    -0.82
     propOrder
    -0.82
    OGND
    -0.76
     وتسجيلات
    -0.72
    kháu
    -0.70
    IsContent
    -0.70
    Personensuche
    -0.69
    BufferException
    -0.69
    POSITIVE LOGITS
     Serikat
    0.43
    glacial
    0.42
    лада
    0.40
    getServer
    0.38
    holidays
    0.38
    tacte
    0.38
    valdi
    0.37
    منابع
    0.37
    までも
    0.36
     thôi
    0.36
    Activations Density 2.230%

    No Known Activations