© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2258
    Prev
    Next
    INDEX
    Explanations

    code syntax containing commas, parenthesis, variable assignments, and "if" statements

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    __*/
    -0.65
     Romains
    -0.61
    rrggbb
    -0.60
     politiet
    -0.59
    MemoryWarning
    -0.59
    @",
    -0.59
    MLLoader
    -0.59
     */,
    -0.58
     billede
    -0.57
     gambe
    -0.57
    POSITIVE LOGITS
    DoubleQuotes
    0.65
     truc
    0.54
    migrationBuilder
    0.52
    rousel
    0.52
    astify
    0.50
    IntoConstraints
    0.49
     afer
    0.49
     br
    0.48
    MessageTagHelper
    0.48
    ⓧ
    0.47
    Activations Density 2.251%

    No Known Activations