© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51872
    Prev
    Next
    INDEX
    Explanations

    Guidewire, Pots, premise

    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_10_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
     fuzz
    0.52
    loadNpm
    0.50
     dataframe
    0.47
     DataFrame
    0.47
     repress
    0.46
    েন
    0.45
    )$,
    0.45
     hik
    0.45
     keter
    0.44
    FRAMERATE
    0.44
    POSITIVE LOGITS
     Avant
    0.54
    Avant
    0.51
     Antes
    0.46
    <0x80>
    0.46
     avant
    0.46
    帏
    0.46
    之际
    0.44
    යෙන්
    0.43
    ская
    0.42
    ères
    0.42
    Activations Density 0.000%

    No Known Activations