© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170210
    Prev
    Next
    INDEX
    Explanations

    Defensive Player of the Year

    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_20_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
     初
    0.33
    ခံ
    0.29
     scoreless
    0.28
    ous
    0.28
     खिलाड़ी
    0.28
    gateTime
    0.28
     الاول
    0.28
     στις
    0.28
     கிட்ட
    0.28
     player
    0.27
    POSITIVE LOGITS
     پاورپوینت
    0.30
    凝
    0.29
    汪
    0.28
     veya
    0.28
    شی
    0.28
     Margot
    0.28
    리로
    0.27
     supernatant
    0.27
     või
    0.26
     erhöhen
    0.26
    Activations Density 0.000%

    No Known Activations