© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46283
    Prev
    Next
    INDEX
    Explanations

    type definitions

    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_22_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
     Treaty
    0.28
     mutants
    0.25
     നടത്ത
    0.25
    对应的
    0.24
    kiego
    0.24
     w
    0.24
     امکان
    0.24
    alanya
    0.24
    kii
    0.23
     लेने
    0.23
    POSITIVE LOGITS
    Favourite
    0.25
    adaş
    0.25
    tm
    0.24
    Baseball
    0.24
    삐
    0.23
     craving
    0.23
    קט
    0.23
    ត្រ
    0.23
    gte
    0.23
    toolbar
    0.23
    Activations Density 0.004%

    No Known Activations