© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 205202
    Prev
    Next
    INDEX
    Explanations

    answers after ---ANSWER KEY---

    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_10_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
    ็บ
    0.64
    มัน
    0.63
     aktual
    0.61
    S
    0.61
    iping
    0.60
     dilwale
    0.60
     aHUS
    0.60
    itation
    0.60
    枚举
    0.60
    plr
    0.58
    POSITIVE LOGITS
     on
    0.77
     for
    0.76
     getSchema
    0.68
    begin
    0.64
    恜
    0.59
     experience
    0.59
    за
    0.59
     entstehen
    0.59
    го
    0.58
     always
    0.57
    Activations Density 0.000%

    No Known Activations