© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135580
    Prev
    Next
    INDEX
    Explanations

    okay, let's

    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_6_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
     a
    1.04
    ations
    1.01
     in
    0.93
    ท
    0.93
    ij
    0.79
     t
    0.79
    ası
    0.78
    in
    0.77
     (
    0.77
    ilt
    0.77
    POSITIVE LOGITS
    おしゃれ
    0.96
    et
    0.93
     Adriana
    0.89
    い
    0.88
     Josep
    0.86
     prefeito
    0.84
     Justine
    0.84
     Melo
    0.82
    多い
    0.81
     Adriano
    0.81
    Activations Density 0.053%

    No Known Activations