© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13539
    Prev
    Next
    INDEX
    Explanations

    words that appear in source code related to modules and filepaths, particularly in JavaScript

    oai_token-act-pair · gemini-2.0-flash

    ticker

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ilova
    -0.52
     Chwiliwch
    -0.50
    BitConverter
    -0.50
     localization
    -0.47
    instal
    -0.46
    Dig
    -0.46
     surla
    -0.46
    Discover
    -0.46
    ьаж
    -0.46
     Pingback
    -0.46
    POSITIVE LOGITS
    ագրություններ
    0.63
     Privacidade
    0.57
    \{\\
    0.56
    AnimationsModule
    0.56
    mybatisplus
    0.55
    脚注の使い方
    0.54
    sendRedirect
    0.53
    tableFuture
    0.53
     Pública
    0.52
     snippetHide
    0.52
    Activations Density 1.595%

    No Known Activations