© 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. 217627
    Prev
    Next
    INDEX
    Explanations

    places and locations

    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
    華
    0.45
    华
    0.44
    holtz
    0.42
     fift
    0.41
    Хо
    0.40
     Whitman
    0.37
     화
    0.37
    raits
    0.36
     重
    0.36
     Maio
    0.36
    POSITIVE LOGITS
    첩
    0.39
     முன்னே
    0.39
    zie
    0.38
     व्य
    0.37
    sup
    0.37
     تضيفلها
    0.37
    omat
    0.35
     Und
    0.35
    ['_
    0.35
    UNDS
    0.35
    Activations Density 0.013%

    No Known Activations