© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 29953
    Prev
    Next
    INDEX
    Explanations

    csv file

    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_7_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
    지
    0.49
    ется
    0.49
    ята
    0.46
    িত
    0.44
    ുവരി
    0.44
    зка
    0.44
    ография
    0.44
     কারা
    0.43
    員
    0.43
    由於
    0.43
    POSITIVE LOGITS
    ing
    1.03
    ik
    0.89
    ter
    0.80
    uk
    0.79
    te
    0.75
    il
    0.75
    ’
    0.72
    sh
    0.65
    ret
    0.65
     and
    0.63
    Activations Density 0.025%

    No Known Activations