© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 195336
    Prev
    Next
    INDEX
    Explanations

    semester

    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_46_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
     कृत
    0.43
    Foreground
    0.39
    era
    0.38
    universe
    0.38
    Dice
    0.37
    UB
    0.36
    ACK
    0.36
    US
    0.36
    უ
    0.35
    Universe
    0.35
    POSITIVE LOGITS
     system
    0.46
     সিস্টেম
    0.46
     dates
    0.45
     Dates
    0.43
     ENC
    0.43
    房間
    0.43
     roomId
    0.42
    रूम
    0.42
     系统
    0.41
     システム
    0.41
    Activations Density 0.001%

    No Known Activations