© 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. 12237
    Prev
    Next
    INDEX
    Explanations

    code syntax and frequently used keywords such as "main", "import", "class", or "#include"

    oai_token-act-pair · gemini-2.0-flash

    brackets/parentheses

    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
    tonsoft
    -0.73
    Hentet
    -0.68
    Bronnen
    -0.65
     ویکی‌پدی
    -0.63
     autorytatywna
    -0.60
     виправивши
    -0.57
     Paglinawan
    -0.57
     lenker
    -0.56
    ViewById
    -0.55
    bewerken
    -0.53
    POSITIVE LOGITS
    ėk
    0.52
     biotite
    0.50
     pleaſure
    0.49
     unſ
    0.49
     oseb
    0.48
     tranſ
    0.48
    PYX
    0.47
     flyknit
    0.47
     hornblende
    0.47
     juſt
    0.46
    Activations Density 6.229%

    No Known Activations