© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 26742
    Prev
    Next
    INDEX
    Explanations

    system, vm, str, list, item

    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_40_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
    ipio
    0.23
    фин
    0.22
    pera
    0.22
    ļ
    0.22
     динами
    0.21
    塊
    0.21
    دين
    0.21
    मोर
    0.21
    mergeddata
    0.21
    煂
    0.21
    POSITIVE LOGITS
     ভেদ
    0.23
     CREATE
    0.22
    Marshal
    0.22
    CREATE
    0.22
     Побе
    0.22
    自从
    0.21
     protested
    0.21
     EEG
    0.21
    marshal
    0.21
    жка
    0.21
    Activations Density 0.002%

    No Known Activations