© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200386
    Prev
    Next
    INDEX
    Explanations

    comfortable shoes

    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_6_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
     arma
    0.88
     effectuées
    0.86
     îng
    0.86
     võib
    0.86
    mingw
    0.86
    chaoxing
    0.84
    imcoords
    0.84
     válv
    0.84
    F
    0.84
    Hua
    0.84
    POSITIVE LOGITS
    in
    1.37
    ar
    1.03
    ।
    1.00
    。
    0.98
    ار
    0.95
     D
    0.93
    de
    0.92
    ্ড
    0.89
     A
    0.87
    d
    0.87
    Activations Density 0.002%

    No Known Activations