© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 103007
    Prev
    Next
    INDEX
    Explanations

    wallet

    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_14_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
    ا
    0.68
     دع
    0.57
    دع
    0.55
    ou
    0.52
    re
    0.51
    ্লিক
    0.51
     rheumatoid
    0.49
     требо
    0.48
    soldiers
    0.47
    la
    0.46
    POSITIVE LOGITS
     microstructure
    0.55
    ","#
    0.53
    विजन
    0.52
     microfiber
    0.52
    %")
    0.52
    {\
    0.51
    ibia
    0.50
    🫧
    0.50
    ąż
    0.48
     mikro
    0.47
    Activations Density 0.001%

    No Known Activations