© 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. 30247
    Prev
    Next
    INDEX
    Explanations

    youtube.com

    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
    不少
    0.59
    v
    0.55
    í
    0.53
    υ
    0.50
    das
    0.49
    id
    0.46
    dar
    0.45
    minent
    0.44
    chedule
    0.43
    ها
    0.43
    POSITIVE LOGITS
    을
    0.63
    া
    0.61
    ৪
    0.60
    a
    0.59
     toBe
    0.58
    t
    0.56
     आणि
    0.55
    uš
    0.55
    に
    0.55
    에
    0.54
    Activations Density 0.006%

    No Known Activations