© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121760
    Prev
    Next
    INDEX
    Explanations

    list items or entities

    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_27_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
     successively
    0.34
     progres
    0.32
     sequentially
    0.31
     turning
    0.31
    progress
    0.31
     progressively
    0.29
     dressed
    0.29
    粗
    0.28
    孔
    0.28
     progressive
    0.28
    POSITIVE LOGITS
     Kinetics
    0.32
     Shed
    0.32
    ၼ
    0.31
    暐
    0.29
     Metallurgy
    0.29
     vlá
    0.28
     Recordemos
    0.28
     паліты
    0.28
     Study
    0.28
    లేదు
    0.28
    Activations Density 0.005%

    No Known Activations