© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205735
    Prev
    Next
    INDEX
    Explanations

    create a new

    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_20_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
     минера
    0.55
     tanpa
    0.54
     Без
    0.53
     Kxg
    0.53
    Ⲥ
    0.52
     económica
    0.52
     волосы
    0.52
     결방
    0.51
     fără
    0.51
     senza
    0.50
    POSITIVE LOGITS
    e
    0.52
    gender
    0.47
    state
    0.47
    type
    0.47
    the
    0.46
    new
    0.45
    describe
    0.45
    does
    0.45
    said
    0.44
    explain
    0.44
    Activations Density 0.006%

    No Known Activations