© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175429
    Prev
    Next
    INDEX
    Explanations

    Gumroad, Lovevery, Jeremy

    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_50_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
     बलराम
    0.50
    Champions
    0.45
    Billy
    0.44
    ឃ
    0.44
    Fold
    0.42
    Bits
    0.42
    BITS
    0.41
    billy
    0.40
    ڏ
    0.40
     Billy
    0.39
    POSITIVE LOGITS
     auc
    0.43
    ࢮ
    0.43
    公式
    0.40
     бла
    0.40
     Substance
    0.39
     肉
    0.38
     مشخص
    0.38
     audited
    0.37
     citation
    0.37
     Guan
    0.37
    Activations Density 0.000%

    No Known Activations