© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 102922
    Prev
    Next
    INDEX
    Explanations

    scale and measurement

    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_1_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
    deki
    1.10
     года
    1.04
    "，
    1.01
    もの
    1.00
     дверь
    0.99
     vlast
    0.98
    臾
    0.97
     тема
    0.96
    も
    0.96
     posición
    0.95
    POSITIVE LOGITS
    ing
    1.42
    ב
    1.26
    ED
    1.23
     for
    1.20
     legitim
    1.20
    z
    1.20
    ل
    1.20
    ↵↵
    1.12
    US
    1.09
    ए
    1.09
    Activations Density 0.003%

    No Known Activations