© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 87459
    Prev
    Next
    INDEX
    Explanations

    say *

    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_60_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
    лка
    0.49
     Flies
    0.47
    flies
    0.46
     Bikes
    0.46
    laşt
    0.45
    larından
    0.43
    b
    0.43
    ↵↵
    0.43
     Six
    0.43
    et
    0.43
    POSITIVE LOGITS
     mid
    0.51
     whitespace
    0.48
     midterm
    0.48
     lanyard
    0.46
     purview
    0.46
     '+
    0.45
     revocation
    0.45
     midline
    0.45
     be
    0.44
     etiology
    0.44
    Activations Density 0.031%

    No Known Activations