© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124403
    Prev
    Next
    INDEX
    Explanations

    rabbit, mall, aquarium, diamonds, content

    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_3_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
     by
    0.84
     for
    0.73
    မြင့်
    0.72
    कृति
    0.68
    2
    0.67
     sạn
    0.65
    وف
    0.65
     Lipschitz
    0.63
     bâ
    0.63
    H
    0.63
    POSITIVE LOGITS
    in
    0.92
    as
    0.89
    น
    0.82
    n
    0.82
    re
    0.81
    at
    0.79
    ن
    0.78
    id
    0.71
    m
    0.70
    u
    0.68
    Activations Density 0.001%

    No Known Activations