© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12240
    Prev
    Next
    INDEX
    Explanations

    a large amount of different words and phrases that do not seem to have a close relationship

    oai_token-act-pair · gemini-2.0-flash

    opinions and judgements

    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
     Wicidata
    -0.61
    AddTagHelper
    -0.60
     torchvision
    -0.54
     samband
    -0.51
     ?>
    -0.51
     insuffisamment
    -0.50
    例句
    -0.47
    stwie
    -0.47
    ?>">
    -0.47
    writeFieldEnd
    -0.47
    POSITIVE LOGITS
    ########.
    0.86
    Geplaatst
    0.68
    {}{
    0.63
    ExecuteReader
    0.62
    npmjs
    0.58
     pasas
    0.54
    yarnpkg
    0.54
    migrationBuilder
    0.53
     typelib
    0.52
    offsetof
    0.51
    Activations Density 6.890%

    No Known Activations