© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 179945
    Prev
    Next
    INDEX
    Explanations

    dominance and submission

    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_50_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
     F
    0.54
    F
    0.46
     मिरची
    0.45
     الف
    0.43
     O
    0.43
    ஏ
    0.42
     Φ
    0.41
     شمار
    0.39
     Κ
    0.39
     Ο
    0.39
    POSITIVE LOGITS
     DPS
    0.43
     DQ
    0.37
     Virg
    0.36
     LIE
    0.36
     Eugenia
    0.35
    襲
    0.35
     एमसीक्यू
    0.34
    ஜீ
    0.34
    Tet
    0.34
     bie
    0.34
    Activations Density 0.010%

    No Known Activations