© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10331
    Prev
    Next
    INDEX
    Explanations

    Chicago citation style

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chatID
    0.38
    degrees
    0.38
     degrees
    0.37
    hofer
    0.37
    Degrees
    0.36
     Degrees
    0.36
     planner
    0.35
     ఓ
    0.34
     stuffing
    0.34
     तरुण
    0.34
    POSITIVE LOGITS
     style
    0.71
     styles
    0.66
    Style
    0.63
    style
    0.62
    スタイル
    0.61
     Style
    0.60
     estilos
    0.59
    styles
    0.59
     Styles
    0.59
     сти
    0.56
    Activations Density 0.002%

    No Known Activations