© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 181293
    Prev
    Next
    INDEX
    Explanations

    file extensions like *.txt, *.sh, *.clad

    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_24_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
    漂亮
    0.17
    স্থানীয়
    0.17
    reader
    0.16
    প্রায়
    0.16
     ليس
    0.15
    rtList
    0.15
     повністю
    0.15
    subsection
    0.15
    ///
    0.15
     ใด
    0.14
    POSITIVE LOGITS
     할인
    0.18
     evaluates
    0.17
     fakult
    0.16
     imdb
    0.15
    čno
    0.15
     candies
    0.15
     choirs
    0.15
     rahu
    0.15
     accuracies
    0.15
     cans
    0.15
    Activations Density 0.000%

    No Known Activations