© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2000
    Prev
    Next
    INDEX
    Explanations

    code snippets and identifiers related to parsing or validating code, potentially in Javascript or Typescript.

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    PerformLayout
    -0.65
    InjectAttribute
    -0.61
    kháu
    -0.60
    SharedDtor
    -0.60
     AssemblyTitle
    -0.57
    principalColumn
    -0.57
    Jeografia
    -0.56
     دیکھیے
    -0.56
    forKey
    -0.53
    parency
    -0.52
    POSITIVE LOGITS
    interopRequire
    0.59
     bang
    0.59
    tslib
    0.56
    classnames
    0.56
    bang
    0.55
    __*/
    0.55
     Вікіпе
    0.54
    ifter
    0.53
    HtmlAttribute
    0.52
    enso
    0.51
    Activations Density 4.790%

    No Known Activations