© 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. 143510
    Prev
    Next
    INDEX
    Explanations

    names and initials

    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
    果た
    0.46
     desempe
    0.44
    getStartState
    0.41
     ಮಾತ
    0.40
     alent
    0.39
    ม่า
    0.39
     прилага
    0.39
    珴
    0.38
    潑
    0.37
    ţă
    0.37
    POSITIVE LOGITS
     EB
    0.43
    EB
    0.41
     अहमद
    0.41
    Et
    0.40
     আহমেদ
    0.38
    Inverse
    0.38
    এইচ
    0.38
     Ahmed
    0.38
     San
    0.37
    ET
    0.37
    Activations Density 0.000%

    No Known Activations