© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10916
    Prev
    Next
    INDEX
    Explanations

    parenthetical notes that express emotion

    oai_token-act-pair · gemini-2.0-flash

    online emotional reactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     للمعارف
    -0.96
    MessageOf
    -0.91
    OGND
    -0.86
     nahilalakip
    -0.73
     ProtoMessage
    -0.71
    webElementXpaths
    -0.71
     ModelExpression
    -0.70
     للاسماء
    -0.68
     Signalez
    -0.66
    انيف
    -0.65
    POSITIVE LOGITS
    PARED
    0.50
    仑
    0.48
     Bahadur
    0.48
     plenti
    0.48
    inheritDoc
    0.47
    kenal
    0.47
    ful
    0.47
    instein
    0.46
    zugehen
    0.46
     SDLK
    0.46
    Activations Density 1.564%

    No Known Activations