© 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. 45134
    Prev
    Next
    INDEX
    Explanations

    boundary between

    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
    ۔
    0.70
    트를
    0.68
     atteindre
    0.67
     blijven
    0.65
     belted
    0.64
     ойнойт
    0.64
     अवधि
    0.64
     examin
    0.64
     ง่าย
    0.64
    पंथी
    0.63
    POSITIVE LOGITS
     the
    0.79
    Calling
    0.73
    Communication
    0.73
     superconductors
    0.72
    Restaurants
    0.72
    f
    0.72
    official
    0.71
    Precision
    0.69
    diamonds
    0.68
    errors
    0.68
    Activations Density 0.035%

    No Known Activations