© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 69368
    Prev
    Next
    INDEX
    Explanations

    specific names

    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_46_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
    dió
    0.39
    SelectList
    0.38
    vrd
    0.38
    enuation
    0.38
    vind
    0.38
    ｖ
    0.37
    вра
    0.37
    onton
    0.36
     tvam
    0.36
    맺
    0.36
    POSITIVE LOGITS
    그램
    0.39
    京
    0.38
     patch
    0.38
     batteria
    0.37
    केवल
    0.37
     நிச்ச
    0.37
     privati
    0.36
     Sydney
    0.36
     konus
    0.36
    ymi
    0.35
    Activations Density 0.005%

    No Known Activations