© 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. 207611
    Prev
    Next
    INDEX
    Explanations

    you

    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
     CPR
    0.43
    决定
    0.39
    ථ
    0.39
     可以
    0.39
     decide
    0.38
     seminar
    0.38
     kör
    0.38
    िक्र
    0.38
    CPR
    0.38
    ೇತ್ರ
    0.38
    POSITIVE LOGITS
    Noah
    0.43
    wasser
    0.43
    翎
    0.39
    strass
    0.39
    жим
    0.37
    ໄຂ
    0.37
     Noah
    0.36
     surely
    0.35
     Mathieu
    0.35
     zeker
    0.35
    Activations Density 0.001%

    No Known Activations