© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7241
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming syntax

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    colgroup
    -0.51
    uman
    -0.48
    <!--[
    -0.46
    dat
    -0.45
    Dat
    -0.45
    fau
    -0.44
    J
    -0.44
    BN
    -0.44
    >{@
    -0.44
     dat
    -0.43
    POSITIVE LOGITS
     Monfieur
    0.74
    SBATCH
    0.73
    IntoConstraints
    0.71
     Shakspeare
    0.71
     Majefty
    0.67
    migrationBuilder
    0.66
    venido
    0.63
     Theſe
    0.62
     referenties
    0.60
    jsxFileName
    0.60
    Activations Density 0.893%

    No Known Activations