© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106470
    Prev
    Next
    INDEX
    Explanations

    one-size-fits-all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_1_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
    ي
    2.05
    p
    1.96
    an
    1.80
    i
    1.76
    ان
    1.73
    w
    1.59
    in
    1.55
    c
    1.48
    و
    1.41
    ج
    1.39
    POSITIVE LOGITS
     a
    0.99
     arugula
    0.96
    ক্ক
    0.96
    ക
    0.96
    ﻮ
    0.96
    岨
    0.96
     I
    0.95
     polytope
    0.92
    izlik
    0.92
     pruž
    0.91
    Activations Density 0.001%

    No Known Activations