© 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. 9936
    Prev
    Next
    INDEX
    Explanations

    attacking football players

    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
     NoContent
    0.40
    バシー
    0.38
    編
    0.38
    carotene
    0.37
     SqlParameter
    0.37
     Wissen
    0.36
    мили
    0.36
    加工
    0.35
     fiscales
    0.35
     QE
    0.35
    POSITIVE LOGITS
     strike
    0.45
     ప్రక
    0.42
    Strike
    0.42
     Strike
    0.42
    ूब
    0.41
     bá
    0.40
     partnership
    0.40
     પ
    0.39
    partnership
    0.39
     சூ
    0.37
    Activations Density 0.032%

    No Known Activations