© 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. 10503
    Prev
    Next
    INDEX
    Explanations

    bpy.ops commands

    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
     Deputy
    0.34
     SDL
    0.34
    миз
    0.34
     UIButton
    0.34
    мих
    0.33
    prochen
    0.33
     замести
    0.33
    ग्विजय
    0.33
    受賞
    0.32
    낙
    0.32
    POSITIVE LOGITS
     BOOKS
    0.38
     tand
    0.37
    tand
    0.37
    cida
    0.37
     flancs
    0.36
     দিচ্ছে
    0.34
     tandem
    0.34
    volle
    0.34
    rVert
    0.34
    泡
    0.34
    Activations Density 0.001%

    No Known Activations