© 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. 8519
    Prev
    Next
    INDEX
    Explanations

    code blocks, especially those ending with a return statement

    oai_token-act-pair · gemini-2.0-flash

    Code-related terms

    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
     return
    -0.60
    return
    -0.60
     Returning
    -0.57
     Return
    -0.55
     returning
    -0.55
    Return
    -0.50
    RETURN
    -0.50
     RETURN
    -0.49
    internalType
    -0.49
     returned
    -0.49
    POSITIVE LOGITS
     MainAxisSize
    0.62
     InputDecoration
    0.62
    BagConstraints
    0.60
    ExtendWith
    0.59
    IntoConstraints
    0.57
    basicConfig
    0.57
    PendingIntent
    0.57
    ValueStyle
    0.54
    migrationBuilder
    0.54
    出版年
    0.54
    Activations Density 1.188%

    No Known Activations