© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5928
    Prev
    Next
    INDEX
    Explanations

    code snippets and related terms like "install", "script", and "version"

    oai_token-act-pair · gemini-2.0-flash

    Code and documentation snippets

    np_max-act-logits · 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
    DockStyle
    -0.69
     समीक्षाओं
    -0.68
    ">//
    -0.67
    featureID
    -0.64
     חיצוניים
    -0.61
     <=",
    -0.60
     Paglinawan
    -0.59
     Specially
    -0.59
    tagHelperRunner
    -0.58
     ویکی‌پدی
    -0.58
    POSITIVE LOGITS
    rubin
    0.51
     TOUR
    0.50
     alimentaires
    0.48
     Tour
    0.48
    Tour
    0.47
    lerc
    0.47
    HasForeignKey
    0.46
    extAlignment
    0.45
     jöv
    0.44
     tour
    0.44
    Activations Density 0.511%

    No Known Activations