© 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. 13999
    Prev
    Next
    INDEX
    Explanations

    text that is separated from the rest of the document (likely by line breaks)

    oai_token-act-pair · 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
    Negative Logits
     appreci
    -0.68
     SqlParameter
    -0.67
    ,
    -0.66
     Hanford
    -0.62
     Winfrey
    -0.61
     agate
    -0.59
     Nuestra
    -0.59
    msub
    -0.59
     reciprocity
    -0.59
    -0.59
    POSITIVE LOGITS
     resourceCulture
    0.93
    verwijspagina
    0.88
     autorytatywna
    0.88
     ModelExpression
    0.85
     مشين
    0.84
     onCreateView
    0.81
     disambiguazione
    0.75
    ↵
    0.74
     
    0.73
    KURZBESCHREIBUNG
    0.70
    Activations Density 2.253%

    No Known Activations