© 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. 9594
    Prev
    Next
    INDEX
    Explanations

    citations of legal documents, scientific publications, and possibly code libraries

    oai_token-act-pair · gemini-2.0-flash

    code and scientific papers

    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
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.62
    <?
    -0.59
    ngdoc
    -0.57
    XMLSchema
    -0.52
    noStroke
    -0.49
     OMITBAD
    -0.49
    Grand
    -0.49
    VisualStudio
    -0.49
    ragan
    -0.48
    QMetaType
    -0.48
    POSITIVE LOGITS
    tvguidetime
    0.61
     peindre
    0.59
     CreateTagHelper
    0.59
     initComponents
    0.58
    ougars
    0.57
    ătoare
    0.56
     Delf
    0.55
    "])){
    0.54
     ब्रेकडाउन
    0.54
    ="@
    0.53
    Activations Density 1.914%

    No Known Activations