© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142749
    Prev
    Next
    INDEX
    Explanations

    punch

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     competitively
    0.43
     competes
    0.41
    זו
    0.40
     competitive
    0.39
     Competitive
    0.37
     Buh
    0.35
    蛋
    0.35
    験
    0.35
    ဇ
    0.35
    激情
    0.34
    POSITIVE LOGITS
     bent
    0.42
    ାର
    0.40
    patch
    0.39
     méth
    0.39
    estimate
    0.39
    ⴷ
    0.39
     patch
    0.38
     fumble
    0.38
    straight
    0.37
     assured
    0.37
    Activations Density 0.002%

    No Known Activations