© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15161
    Prev
    Next
    INDEX
    Explanations

    question words

    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_13_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
    砧
    0.40
     పుస్త
    0.35
    ពិ
    0.34
     وجدت
    0.34
     الرياضيات
    0.33
    qui
    0.33
    sterdam
    0.32
    개의
    0.32
    spunkt
    0.31
    會議
    0.31
    POSITIVE LOGITS
     refinance
    0.42
    ル
    0.38
    ecido
    0.37
     currency
    0.36
    ੋਂ
    0.35
    コスト
    0.35
    ویی
    0.35
     mistress
    0.35
     refinancing
    0.35
     mortgage
    0.34
    Activations Density 0.085%

    No Known Activations