© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15905
    Prev
    Next
    INDEX
    Explanations

    interjections, acknowledgements, and discourse markers in conversational text.

    oai_token-act-pair · gemini-2.0-flash

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    es
    -0.47
    ism
    -0.46
     (
    -0.46
    e
    -0.45
    K
    -0.44
    """
    -0.44
    line
    -0.44
    ;
    -0.43
    */
    -0.43
    is
    -0.43
    POSITIVE LOGITS
    StoryboardSegue
    1.10
     Jefus
    1.05
    IntoConstraints
    1.03
    ^(@)
    0.94
     myſelf
    0.93
     Efq
    0.93
    SourceChecksum
    0.90
     betweenstory
    0.90
     ModelExpression
    0.88
     houſe
    0.88
    Activations Density 11.015%

    No Known Activations