© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48560
    Prev
    Next
    INDEX
    Explanations

    Sudan conflict

    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_55_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
    میم
    0.40
     બનાવે
    0.40
     পছ
    0.38
    Preferences
    0.37
    mapsto
    0.37
     यो
    0.37
     Cheyenne
    0.37
    ⬆
    0.37
     Prev
    0.36
    oplas
    0.36
    POSITIVE LOGITS
    拨款
    0.38
    タイトル
    0.37
    复杂度
    0.37
     critiques
    0.36
     педагоги
    0.36
    วรร
    0.36
     అధ్యక్ష
    0.36
     complexity
    0.35
     Constitutional
    0.35
     ഇന്ത്യന്‍
    0.35
    Activations Density 0.004%

    No Known Activations