© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3788
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially method definitions and overrides, possibly in Java

    oai_token-act-pair · gemini-2.0-flash

    code annotations and method definitions

    np_token-act-pair-logits · gpt-4o-mini

    public/protected

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    tagHelperRunner
    -0.82
    migrationBuilder
    -0.57
    Tikang
    -0.55
    )++;
    -0.51
     AssemblyCulture
    -0.50
    WEBPACK
    -0.49
    htë
    -0.49
    character
    -0.47
    ."],
    -0.47
    indow
    -0.47
    POSITIVE LOGITS
    Personensuche
    0.64
    CONCURRENT
    0.58
     ویکی‌پدیا
    0.49
    ⓧ
    0.49
    UnknownFieldSet
    0.49
    VIAF
    0.47
     Pamp
    0.47
     Locking
    0.47
    Bises
    0.46
     Perlu
    0.46
    Activations Density 0.352%

    No Known Activations