© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 129783
    Prev
    Next
    INDEX
    Explanations

    gu sound

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    翩
    0.40
    haben
    0.39
    られた
    0.38
    pexels
    0.38
    летним
    0.37
     alken
    0.37
    ीजन
    0.36
     Pflanzen
    0.35
     hosped
    0.35
    hInstance
    0.35
    POSITIVE LOGITS
     гу
    1.20
     Гу
    1.18
    Gu
    1.17
     gua
    1.08
     gu
    1.06
     グ
    1.03
     guild
    1.02
     Gu
    1.01
     Gua
    0.97
    gu
    0.97
    Activations Density 0.001%

    No Known Activations