© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14598
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS code, targeting Bootstrap elements, color definitions, and Javascript display functions

    oai_token-act-pair · gemini-2.0-flash

    red

    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
     roll
    -0.41
     an
    -0.40
     scale
    -0.40
    yson
    -0.39
     right
    -0.39
     most
    -0.39
     zapo
    -0.39
     intended
    -0.38
    **/
    -0.38
    ahnya
    -0.38
    POSITIVE LOGITS
    ThroughAttribute
    1.03
    windowFixed
    0.91
    EDEFAULT
    0.91
    rawDesc
    0.83
    StoryboardSegue
    0.82
    MigrationBuilder
    0.82
    RegistryLite
    0.82
    WebServlet
    0.80
     '\\;'
    0.79
    LookAnd
    0.78
    Activations Density 2.132%

    No Known Activations