© 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. 221419
    Prev
    Next
    INDEX
    Explanations

    YouTube channel names

    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
     какая
    0.33
    кци
    0.31
    фия
    0.31
    —“
    0.31
    CardArray
    0.30
    鲁
    0.30
    XSSFSheet
    0.30
     structs
    0.29
     UIView
    0.29
     %>'
    0.29
    POSITIVE LOGITS
     Streets
    0.34
     دار
    0.33
     posled
    0.32
     Dar
    0.32
     непре
    0.32
     suitcase
    0.32
     munch
    0.31
    성과
    0.31
    즘
    0.31
     destin
    0.30
    Activations Density 0.001%

    No Known Activations