© 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. 1022
    Prev
    Next
    INDEX
    Explanations

    question marks and maybe exclamation points

    oai_token-act-pair · gemini-2.0-flash

    question marks

    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
     measure
    -1.14
     indicators
    -1.09
     metric
    -1.07
     metrics
    -1.07
    Measure
    -1.02
     indicator
    -1.00
    measure
    -1.00
     Indicators
    -0.97
     Measure
    -0.95
     measures
    -0.93
    POSITIVE LOGITS
    ніципалі
    0.80
     GIPHY
    0.67
    DoubleQuotes
    0.64
     Hift
    0.59
     tongs
    0.59
     Compulsory
    0.57
     houſe
    0.57
     Quid
    0.57
     ſche
    0.57
    تقاوى
    0.56
    Activations Density 0.728%

    No Known Activations