© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62717
    Prev
    Next
    INDEX
    Explanations

    righting things, rotors, mountain, bits

    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_2_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
    ير
    1.75
    v
    1.67
    ри
    1.59
    人
    1.49
    ss
    1.36
    ot
    1.35
    ها
    1.33
    خ
    1.33
    .
    1.29
    od
    1.27
    POSITIVE LOGITS
     decentral
    1.21
     scrutin
    1.09
     complainant
    1.08
    াৰ
    1.04
     objected
    1.03
     indignation
    1.03
    ीडियो
    1.02
    지와
    1.02
     replies
    1.01
     decipher
    1.01
    Activations Density 0.001%

    No Known Activations