© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113264
    Prev
    Next
    INDEX
    Explanations

    rock n' roll

    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_2_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
    н
    1.21
     that
    1.16
     œufs
    1.15
     eradicate
    1.13
    {
    1.13
     выпуска
    1.09
     ancien
    1.09
     efectu
    1.09
     insinu
    1.08
     коллеги
    1.07
    POSITIVE LOGITS
    ри
    1.33
    是
    1.28
    การ
    1.26
    기
    1.17
    )。
    1.15
    दायी
    1.04
    ”。
    1.01
    는
    1.01
    الم
    0.99
    야
    0.99
    Activations Density 0.000%

    No Known Activations