© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8068
    Prev
    Next
    INDEX
    Explanations

    combat sports and fighting moves

    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
     akust
    0.37
     Regression
    0.36
     acúst
    0.35
     criticality
    0.34
     FLE
    0.34
    IdleSync
    0.33
    ᵘ
    0.33
    }]}
    0.33
    ständ
    0.33
     bottlene
    0.33
    POSITIVE LOGITS
     knockout
    1.00
     KO
    0.90
    KO
    0.81
     Boxing
    0.78
     Muay
    0.77
     boxing
    0.77
     Knock
    0.73
     knock
    0.72
     knockdown
    0.70
    Boxing
    0.70
    Activations Density 0.021%

    No Known Activations