© 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. 154272
    Prev
    Next
    INDEX
    Explanations

    Am

    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
    cation
    0.42
    价
    0.40
    tik
    0.40
    arquia
    0.39
    мето
    0.39
    timer
    0.39
    弋
    0.38
    विधान
    0.37
    ForRule
    0.37
    പ്പു
    0.37
    POSITIVE LOGITS
     г
    0.46
     g
    0.43
     loc
    0.42
    Գ
    0.42
    G
    0.38
     tup
    0.38
     ग
    0.38
    ardless
    0.38
     loca
    0.38
     reluctantly
    0.37
    Activations Density 0.001%

    No Known Activations