© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 120752
    Prev
    Next
    INDEX
    Explanations

    attacking and dealing damage

    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_38_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
     attempted
    0.39
     ABOVE
    0.39
    стю
    0.39
     Ο
    0.38
     cassettes
    0.37
    vej
    0.37
    areas
    0.36
     tentativas
    0.35
    above
    0.35
    雰
    0.35
    POSITIVE LOGITS
     apopt
    0.41
     neut
    0.40
    Roll
    0.39
     Mulligan
    0.37
    kre
    0.37
    ウィン
    0.36
     لعبة
    0.36
     وین
    0.36
     player
    0.35
    Marks
    0.35
    Activations Density 0.001%

    No Known Activations