© 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. 103020
    Prev
    Next
    INDEX
    Explanations

    return value render json code

    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
     кам
    0.57
     keepsake
    0.57
     desesper
    0.57
     littered
    0.51
    紘
    0.50
     dwind
    0.49
     zoek
    0.49
     patchy
    0.49
     glimmer
    0.48
     parr
    0.47
    POSITIVE LOGITS
    <
    0.61
    Lie
    0.58
    أ
    0.58
    지만
    0.55
    För
    0.55
    =\
    0.55
    Ch
    0.55
    Ш
    0.55
    तो
    0.54
    akai
    0.54
    Activations Density 0.000%

    No Known Activations