© 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. 194915
    Prev
    Next
    INDEX
    Explanations

    say "%"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    대
    0.39
     centralized
    0.38
     central
    0.37
    expo
    0.36
    GE
    0.36
     대
    0.36
    ge
    0.36
     residential
    0.36
    ゚
    0.35
    게
    0.35
    POSITIVE LOGITS
     MOD
    0.65
     मॉड
    0.59
    Mod
    0.58
     Mod
    0.56
    MOD
    0.54
    mod
    0.50
     мод
    0.48
     mód
    0.47
     modulates
    0.47
     modernas
    0.47
    Activations Density 0.000%

    No Known Activations