© 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. 215017
    Prev
    Next
    INDEX
    Explanations

    production planning optimize

    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
    Assistant
    0.41
    ведено
    0.40
     डाली
    0.39
    ận
    0.39
    望着
    0.39
    ánto
    0.39
    Along
    0.38
     заработной
    0.38
    Sunset
    0.38
    舺
    0.38
    POSITIVE LOGITS
     mode
    0.44
     humoral
    0.44
     restful
    0.43
     adher
    0.41
     ambassador
    0.40
     ambiguous
    0.40
     mental
    0.40
     modes
    0.40
     conformity
    0.39
     vert
    0.39
    Activations Density 0.003%

    No Known Activations