© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3299
    Prev
    Next
    INDEX
    Explanations

    scientific texts describing processes

    oai_token-act-pair · gemini-2.0-flash

    applied, passed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     betweenstory
    -0.95
     Мексичка
    -0.93
     vectorielles
    -0.91
    KommentareTeilen
    -0.82
    Autoritní
    -0.78
    GraphicsUnit
    -0.77
     незавершена
    -0.77
     ainfi
    -0.75
     plufieurs
    -0.75
    
    -0.75
    POSITIVE LOGITS
    mstyle
    0.54
     top
    0.53
     getItemId
    0.48
     extra
    0.47
     pr
    0.46
     constantly
    0.46
     tec
    0.45
     unique
    0.45
     rou
    0.45
     fe
    0.45
    Activations Density 1.785%

    No Known Activations