© 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. 19098
    Prev
    Next
    INDEX
    Explanations

    print statement following parenthesis

    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
     toma
    0.25
     tomatoes
    0.25
     tomato
    0.25
    惪
    0.24
    itati
    0.23
     поми
    0.23
     tomate
    0.23
    カテゴリ
    0.23
     nigris
    0.22
    ૮
    0.22
    POSITIVE LOGITS
    now
    0.24
     out
    0.23
    出来
    0.22
    出來
    0.22
    skim
    0.21
     ഗോ
    0.21
     comunicar
    0.21
    मोन
    0.21
    knings
    0.21
     خبر
    0.21
    Activations Density 0.028%

    No Known Activations