© 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. 134191
    Prev
    Next
    INDEX
    Explanations

    on

    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
    Negative Logits
    ਪਣ
    0.38
    सु
    0.35
    גן
    0.35
    करी
    0.35
     کررہے
    0.35
    rey
    0.34
     blocked
    0.34
    ሪ
    0.34
    ^{*
    0.33
    ocy
    0.33
    POSITIVE LOGITS
     adresu
    0.42
    nomenclature
    0.41
    慝
    0.39
     अदर
    0.38
    랬
    0.38
     மற
    0.37
    ád
    0.37
     COMB
    0.37
     совокуп
    0.37
    bě
    0.36
    Activations Density 0.001%

    No Known Activations