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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34819
    Prev
    Next
    INDEX
    Explanations

    w/

    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
    нку
    0.61
     клави
    0.58
    0
    0.57
    
    0.57
    ο
    0.56
    й
    0.54
    leyin
    0.54
     וח
    0.54
    ۰
    0.54
    walker
    0.52
    POSITIVE LOGITS
    i
    0.83
    re
    0.82
    in
    0.71
    ne
    0.69
    。）
    0.66
    dengan
    0.63
    d
    0.63
    m
    0.63
    ）
    0.62
     Oahu
    0.61
    Activations Density 0.001%

    No Known Activations