© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39878
    Prev
    Next
    INDEX
    Explanations

    select all

    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_3_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
     २
    0.62
     SizedBox
    0.61
    น
    0.59
     ९
    0.58
     Mungkin
    0.57
    CTOGRAM
    0.56
     Ở
    0.56
    دی
    0.55
     ३
    0.55
    tive
    0.55
    POSITIVE LOGITS
    м
    1.05
    е
    0.87
    и
    0.86
    ين
    0.79
    ч
    0.78
    í
    0.75
    い
    0.75
    ме
    0.72
     in
    0.72
    й
    0.71
    Activations Density 0.006%

    No Known Activations