© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 128917
    Prev
    Next
    INDEX
    Explanations

    fuzzy matching or logic

    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_1_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
    '
    1.50
    ak
    1.45
    s
    1.30
    ’
    1.23
    la
    1.18
    sh
    1.13
    na
    1.13
    ni
    1.09
    ot
    1.08
    ningen
    1.05
    POSITIVE LOGITS
     afferma
    1.03
    nél
    1.00
    ")):
    0.94
    ۔
    0.94
     беше
    0.94
    는
    0.93
    ી
    0.89
     quizá
    0.89
     actúa
    0.89
     они
    0.89
    Activations Density 0.000%

    No Known Activations