© 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. 210455
    Prev
    Next
    INDEX
    Explanations

    past + following context

    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
     ถึง
    0.66
     overlapped
    0.64
    ,’
    0.61
    ↵↵
    0.60
    ம்
    0.59
    м
    0.58
     engulfed
    0.57
     Vedas
    0.57
     occupied
    0.55
     obs
    0.55
    POSITIVE LOGITS
    r
    0.75
    u
    0.73
    하는
    0.70
    i
    0.70
    Tổng
    0.67
    蘄
    0.66
    materials
    0.66
    persons
    0.64
    性
    0.64
    stress
    0.64
    Activations Density 0.001%

    No Known Activations