© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135436
    Prev
    Next
    INDEX
    Explanations

    all so, all reside, all commonly, all human, all too

    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_6_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
     город
    0.64
     multig
    0.59
     кораб
    0.56
     собствен
    0.55
     उपायों
    0.52
    。<
    0.52
     социа
    0.52
     раствора
    0.51
     entièrement
    0.50
     часу
    0.50
    POSITIVE LOGITS
    ad
    1.05
    ;
    1.02
    i
    0.94
    ed
    0.92
    f
    0.89
    z
    0.89
    ak
    0.86
    at
    0.84
    ut
    0.81
    ah
    0.80
    Activations Density 0.005%

    No Known Activations