© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 88606
    Prev
    Next
    INDEX
    Explanations

    oxygen and nutrients

    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_11_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
     defList
    0.64
     അല്ല
    0.54
    شی
    0.52
     પ
    0.52
    Hval
    0.51
     swirls
    0.50
    мут
    0.49
     wavelengths
    0.48
     antecedent
    0.48
     accomplishments
    0.48
    POSITIVE LOGITS
     on
    0.55
    for
    0.50
    on
    0.49
     incline
    0.49
     Wherever
    0.48
     PPC
    0.48
    眼
    0.47
     Sculpture
    0.46
     Angeles
    0.46
     Save
    0.46
    Activations Density 0.000%

    No Known Activations