© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7476
    Prev
    Next
    INDEX
    Explanations

    economics/leadership journals.

    oai_token-act-pair · gemini-2.0-flash

    say style

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     style
    -2.84
     Style
    -2.83
     STYLE
    -2.70
     styles
    -2.63
    Style
    -2.61
    style
    -2.52
     Styles
    -2.48
    STYLE
    -2.45
    styles
    -2.23
    Styles
    -2.20
    POSITIVE LOGITS
    ArgumentParser
    0.63
     ligiloj
    0.57
    Spoljašnje
    0.56
     nube
    0.54
     odkazy
    0.53
    lapi
    0.50
    AutoField
    0.49
    rapeau
    0.49
    setArguments
    0.49
    ಿಕ
    0.49
    Activations Density 1.396%

    No Known Activations