© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247336
    Prev
    Next
    INDEX
    Explanations

    ability of

    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_40_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
    競爭
    0.46
     ham
    0.44
    Addition
    0.42
    ܩ
    0.39
    addition
    0.39
    Ra
    0.38
    Galer
    0.37
     إضافة
    0.37
    單
    0.37
     Addition
    0.37
    POSITIVE LOGITS
     ঈশ্বর
    0.40
    upi
    0.38
    abola
    0.38
     Gober
    0.37
     précip
    0.37
     almighty
    0.37
    gri
    0.36
    startGame
    0.36
     تازہ
    0.35
    EndTime
    0.35
    Activations Density 0.000%

    No Known Activations