© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 23983
    Prev
    Next
    INDEX
    Explanations

    release date

    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_10_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
     You
    0.84
    ↵
    0.79
    т
    0.77
     can
    0.77
    ت
    0.76
     Burundi
    0.75
    ת
    0.72
     Captain
    0.70
    м
    0.70
     Don
    0.69
    POSITIVE LOGITS
     lidt
    0.56
     ventes
    0.55
    銷售
    0.55
    ished
    0.54
     workloads
    0.53
    專輯
    0.52
    routine
    0.52
     unprofitable
    0.52
    는
    0.51
    irable
    0.51
    Activations Density 0.030%

    No Known Activations