© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 15572
    Prev
    Next
    INDEX
    Explanations

    a wide variety of concepts, including chemical reactions mixing with certain actions, binding of molecules, electric input, legal processes, cooking/recipes, invasion, and general physical state or presence of an object.

    oai_token-act-pair · gemini-2.0-flash

    processes

    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
    OPLE
    -0.56
     chóng
    -0.54
     écoulé
    -0.50
     Rinse
    -0.50
     Voters
    -0.49
     PARSER
    -0.47
     КП
    -0.46
    ẾT
    -0.46
    tagext
    -0.46
    entlichen
    -0.46
    POSITIVE LOGITS
    homonymie
    0.72
    ngOnInit
    0.60
     snippetHide
    0.58
    Xna
    0.56
    клопе
    0.56
    +#+
    0.54
    uxxxx
    0.53
    windowFixed
    0.49
    errHandler
    0.48
    waitKey
    0.48
    Activations Density 0.616%

    No Known Activations