© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127837
    Prev
    Next
    INDEX
    Explanations

    battle, fight, comparison

    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_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     reject
    0.36
     ম্যাক
    0.36
     dSample
    0.36
     rejection
    0.35
    reject
    0.35
    ovač
    0.35
    aronne
    0.35
     kształ
    0.34
    routingHeader
    0.34
     近
    0.34
    POSITIVE LOGITS
     battle
    1.17
     battles
    1.02
     battling
    1.02
    battle
    1.01
     duel
    1.01
     fight
    1.00
    fight
    0.98
     battled
    0.98
     duelo
    0.96
     Battle
    0.90
    Activations Density 0.167%

    No Known Activations