© 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. 181295
    Prev
    Next
    INDEX
    Explanations

    `ROW_NUMBER()` or `RANK()` window functions

    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
    however
    0.43
    ppe
    0.42
    Drake
    0.42
    捎
    0.41
    实习
    0.41
     ছোট্ট
    0.41
    notepad
    0.41
     embarazada
    0.41
    implemented
    0.41
    È
    0.41
    POSITIVE LOGITS
    鵰
    0.38
     wreath
    0.38
     verdict
    0.38
     verdicts
    0.38
     obsc
    0.37
    তান
    0.37
     Disabilities
    0.37
    氣
    0.36
     toning
    0.36
    方面的
    0.36
    Activations Density 0.001%

    No Known Activations