© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 64177
    Prev
    Next
    INDEX
    Explanations

    man

    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_59_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
     dậy
    0.41
    инг
    0.38
    平
    0.37
    家
    0.37
    ंझ
    0.35
    ילה
    0.35
    𒉡
    0.35
    葬
    0.34
     Servi
    0.34
     எதி
    0.34
    POSITIVE LOGITS
    ages
    1.83
    ے
    1.29
    aciones
    1.25
    AGES
    1.08
    age
    1.02
    rooms
    0.95
    room
    0.75
    backs
    0.74
    comings
    0.68
    েন
    0.66
    Activations Density 0.001%

    No Known Activations