© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 34941
    Prev
    Next
    INDEX
    Explanations

    energy efficiency and saving

    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_11_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
    с
    0.56
    pound
    0.50
    нинград
    0.50
    вершен
    0.49
    ной
    0.49
    нил
    0.48
    アーカイブ
    0.48
    黝
    0.47
     бай
    0.47
     izin
    0.47
    POSITIVE LOGITS
     mínima
    0.55
    ES
    0.54
     minima
    0.54
     medals
    0.51
     pamphlets
    0.51
     apathy
    0.50
     wines
    0.50
     organs
    0.49
    OS
    0.49
     wigs
    0.49
    Activations Density 0.032%

    No Known Activations