© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15560
    Prev
    Next
    INDEX
    Explanations

    technical language from scientific and and legal documents including numbers, case names, chemical compounds and measurement abbreviations.

    oai_token-act-pair · 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
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.57
    发表于
    -0.56
     begitu
    -0.53
    onSave
    -0.52
    եց
    -0.51
    րջ
    -0.49
    ="-
    -0.47
     Kong
    -0.47
    kosh
    -0.47
     -$
    -0.46
    POSITIVE LOGITS
    TagMode
    0.73
     {
    0.68
    )";
    0.67
    )");
    0.66
    ScopeManager
    0.63
    Fordítás
    0.63
    rungsseite
    0.63
    ')")
    0.61
    \{\\
    0.61
     {
    0.60
    Activations Density 3.257%

    No Known Activations