© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102754
    Prev
    Next
    INDEX
    Explanations

    "choose", "fined", "has a"

    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_14_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
    tu
    0.58
    seye
    0.52
    io
    0.49
    Association
    0.48
    toc
    0.48
    developers
    0.47
    isters
    0.47
    endale
    0.46
    pt
    0.46
    {#
    0.46
    POSITIVE LOGITS
     novos
    0.54
     Vamos
    0.51
     poetry
    0.49
     poems
    0.49
     Umesh
    0.49
     equivoc
    0.49
     criticisms
    0.46
     mantras
    0.45
     GSM
    0.45
     poem
    0.44
    Activations Density 0.000%

    No Known Activations