© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 218929
    Prev
    Next
    INDEX
    Explanations

    Marco Polo, Joan of Arc, Vlad, Wallace

    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_16_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
    ล
    0.57
    Z
    0.54
    l
    0.52
    RO
    0.52
    EL
    0.52
    ل
    0.52
     يمكن
    0.51
    AR
    0.50
    ])
    0.49
    ت
    0.49
    POSITIVE LOGITS
     smugglers
    0.54
     plough
    0.52
     діяльності
    0.51
     činn
    0.51
     revolved
    0.50
     অ্যান্ট
    0.50
     smuggling
    0.48
     Tama
    0.48
     Unterkunft
    0.47
     smuggled
    0.47
    Activations Density 0.006%

    No Known Activations