© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15720
    Prev
    Next
    INDEX
    Explanations

    code-related tokens, including variable names, classes, and XML parsing

    oai_token-act-pair · gemini-2.0-flash

    code processing/configuration

    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
    Negative Logits
    ↘
    -0.54
    addGap
    -0.52
     Brea
    -0.51
    enzio
    -0.51
    port
    -0.50
    autoreleasepool
    -0.49
     MUD
    -0.47
     Infór
    -0.46
     Wirth
    -0.46
     Bann
    -0.46
    POSITIVE LOGITS
     nahilalakip
    0.45
    KURZBESCHREIBUNG
    0.44
     disambiguazione
    0.41
     kasarigan
    0.40
    UrlResolution
    0.40
    MemoryWarning
    0.39
     समीक्षाओं
    0.38
     חיצוניים
    0.38
    Искәрмәләр
    0.38
    Legături
    0.37
    Activations Density 0.193%

    No Known Activations