© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 81295
    Prev
    Next
    INDEX
    Explanations

    list of numbers followed by comma

    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_31_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
     অবজারভার
    0.37
     Jerseys
    0.34
    cesz
    0.32
    irà
    0.32
    玳
    0.32
     '.$
    0.31
    ट्टे
    0.31
     JERSEY
    0.31
    getCamera
    0.31
    chaften
    0.31
    POSITIVE LOGITS
     tanpa
    0.43
     jealousy
    0.41
    农
    0.39
    льня
    0.38
     Ports
    0.38
     unthinkable
    0.38
     nav
    0.36
     protocolo
    0.36
     without
    0.36
     мои
    0.36
    Activations Density 0.004%

    No Known Activations