© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15018
    Prev
    Next
    INDEX
    Explanations

    code-related keywords such as types, expressions and function calls

    oai_token-act-pair · gemini-2.0-flash

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    InjectAttribute
    -0.80
    Демографія
    -0.70
    getMinutes
    -0.68
    RectangleBorder
    -0.67
    WireFormatLite
    -0.64
    hdashline
    -0.60
    migrationBuilder
    -0.60
    İstinadlar
    -0.59
    دانشنامهٔ
    -0.59
    MessageTagHelper
    -0.59
    POSITIVE LOGITS
    Состав
    0.62
    Regie
    0.45
    迦
    0.44
    recto
    0.44
     CreateTagHelper
    0.43
    binar
    0.43
    <em>
    0.42
     запо
    0.42
    unat
    0.42
     guz
    0.41
    Activations Density 29.554%

    No Known Activations