© 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. 176672
    Prev
    Next
    INDEX
    Explanations

    monitoring

    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
     ờ
    0.53
     Barcelona
    0.48
     ഗവേഷ
    0.45
    กรณ์
    0.44
    ཝ
    0.44
     nějak
    0.44
     stali
    0.44
    셰
    0.44
     পরী
    0.43
     planète
    0.43
    POSITIVE LOGITS
    feet
    0.45
    Aud
    0.44
    thias
    0.44
    TRY
    0.43
    yel
    0.43
    yth
    0.42
    ified
    0.42
    ってい
    0.41
    filesystem
    0.41
     feet
    0.41
    Activations Density 0.004%

    No Known Activations