© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192320
    Prev
    Next
    INDEX
    Explanations

    booths or boathouses

    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_4_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
    ل
    1.53
    ल
    1.23
    s
    1.20
    ut
    1.13
    el
    1.12
    h
    1.09
    t
    1.07
    z
    1.05
    k
    1.03
    ro
    0.92
    POSITIVE LOGITS
    는
    1.02
    τή
    1.00
    렇게
    0.97
    ية
    0.89
    ции
    0.88
    知らせ
    0.88
    ваме
    0.86
    тор
    0.84
    려고
    0.82
    он
    0.82
    Activations Density 0.001%

    No Known Activations