© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121576
    Prev
    Next
    INDEX
    Explanations

    上海外服

    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_3_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
    am
    0.80
    ab
    0.79
    ل
    0.75
    ant
    0.70
    ert
    0.67
    au
    0.65
    upper
    0.65
    itches
    0.64
    l
    0.64
    in
    0.64
    POSITIVE LOGITS
    يل
    0.99
     نہيں
    0.77
     injure
    0.75
    وني
    0.75
    اني
    0.74
     intégr
    0.74
    ）.
    0.73
     politique
    0.73
    جي
    0.73
    زيد
    0.73
    Activations Density 0.001%

    No Known Activations