© 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. 14120
    Prev
    Next
    INDEX
    Explanations

    code snippets containing curly braces

    oai_token-act-pair · gemini-2.0-flash

    bracket

    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
    Negative Logits
    {
    -1.73
    {~
    -0.76
    {\
    -0.71
    {(-
    -0.65
    anskrit
    -0.56
    {.
    -0.56
    {|
    -0.53
    {//
    -0.52
    mtliche
    -0.52
    .
    -0.50
    POSITIVE LOGITS
    <bos>
    1.43
    '])){
    0.92
    ']))
    0.87
     AssemblyCulture
    0.80
    MigrationBuilder
    0.79
    complexContent
    0.79
    __':
    0.77
    <?
    0.76
    GEBURTSDATUM
    0.75
    ({
    0.74
    Activations Density 0.718%

    No Known Activations