© 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. 30475
    Prev
    Next
    INDEX
    Explanations

    second in command

    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
     над
    0.54
    нова
    0.53
     ardından
    0.50
    ↵
    0.50
    ruits
    0.50
     nightclubs
    0.50
    к
    0.49
    ματος
    0.48
     remarked
    0.48
    -
    0.48
    POSITIVE LOGITS
    t
    1.01
    é
    0.82
     \
    0.67
    ו
    0.57
    و
    0.57
    en
    0.52
    em
    0.52
    m
    0.52
    एं
    0.50
    ")
    0.50
    Activations Density 0.002%

    No Known Activations