© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78310
    Prev
    Next
    INDEX
    Explanations

    paraguay, baguette, aguas

    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_0_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
     be
    2.06
     for
    1.77
     in
    1.62
     been
    1.62
     {
    1.48
     he
    1.45
     it
    1.43
    a
    1.43
     b
    1.41
     p
    1.41
    POSITIVE LOGITS
     ennemis
    1.45
     aplatis
    1.37
    ят
    1.36
     органів
    1.32
     arbres
    1.25
    स्ट
    1.22
    лло
    1.21
     árboles
    1.20
     espèces
    1.20
     atletas
    1.19
    Activations Density 0.001%

    No Known Activations