© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27984
    Prev
    Next
    INDEX
    Explanations

    listen to your body

    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_10_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
    in
    0.93
    de
    0.90
    (
    0.86
    +
    0.80
    >
    0.77
    us
    0.75
    A
    0.75
    ate
    0.71
    ون
    0.71
    ми
    0.68
    POSITIVE LOGITS
     MATHEMAT
    0.76
     ಬಿ
    0.71
     沒有
    0.71
    ورية
    0.71
     Música
    0.70
    洌
    0.69
     difficile
    0.68
    '}$
    0.68
     mógł
    0.68
     ಏಕೆಂದರೆ
    0.68
    Activations Density 0.014%

    No Known Activations