© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10587
    Prev
    Next
    INDEX
    Explanations

    text formatting, especially whitespace, indentation, and line breaks, and also finds parenthetical remarks.

    oai_token-act-pair · gemini-2.0-flash

    Forum/comment text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     protoimpl
    -0.87
    SourceChecksum
    -0.85
    StoreMessageInfo
    -0.70
     виправивши
    -0.69
     chi̍t
    -0.63
     useStyles
    -0.63
     Efq
    -0.61
     betweenstory
    -0.61
     ModelExpression
    -0.60
    tagHelperRunner
    -0.59
    POSITIVE LOGITS
    </s>
    0.60
    <b>
    0.54
    I
    0.54
    <h5>
    0.54
    —————
    0.53
    <th>
    0.52
    <strong>
    0.52
    After
    0.50
    ——
    0.50
    Література
    0.50
    Activations Density 7.086%

    No Known Activations