© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16359
    Prev
    Next
    INDEX
    Explanations

    a mix of seemingly unrelated code terms, abbreviations, and function names.

    oai_token-act-pair · gemini-2.0-flash

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    WriteTagHelper
    -0.83
    <bos>
    -0.81
    AddTagHelper
    -0.73
    principalColumn
    -0.71
    ANTLR
    -0.70
     nakalista
    -0.69
    saraba
    -0.69
    olastic
    -0.69
     '\\;'
    -0.67
    ArgsConstructor
    -0.65
    POSITIVE LOGITS
    .
    0.40
    ,
    0.38
    im
    0.35
    넷
    0.34
    <eos>
    0.34
     per
    0.34
     sexual
    0.34
     times
    0.34
     rambut
    0.33
     Arhivirano
    0.32
    Activations Density 15.162%

    No Known Activations