© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46433
    Prev
    Next
    INDEX
    Explanations

    ISO 26262 or ISO 9001 requirements

    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_22_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
    Pine
    0.36
     Leia
    0.33
     Великой
    0.32
     Terence
    0.32
     decades
    0.31
    ǔ
    0.31
    Duration
    0.31
     Pine
    0.30
    uva
    0.30
     William
    0.29
    POSITIVE LOGITS
    קור
    0.38
    جب
    0.32
    চ্ছি
    0.32
    叡
    0.31
    娼
    0.31
    indexBuffer
    0.31
     quais
    0.30
    gments
    0.30
    営業
    0.30
     demolition
    0.30
    Activations Density 0.001%

    No Known Activations