© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14931
    Prev
    Next
    INDEX
    Explanations

    code syntax, specifically looking for conditional statements and array/list operations with sizes

    oai_token-act-pair · gemini-2.0-flash

    zero/0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ########.
    -0.95
    InjectAttribute
    -0.92
    UnusedPrivate
    -0.90
    XMLSchema
    -0.85
     الرياضيه
    -0.83
    Personensuche
    -0.82
    GraphicsUnit
    -0.81
    providedIn
    -0.81
    पया
    -0.80
     propOrder
    -0.79
    POSITIVE LOGITS
    ↵
    0.49
    фель
    0.43
     Upton
    0.42
    sé
    0.41
     fides
    0.40
    וני
    0.39
    seb
    0.39
    msgSender
    0.39
    enetic
    0.39
    те
    0.39
    Activations Density 0.179%

    No Known Activations