© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198116
    Prev
    Next
    INDEX
    Explanations

    well fit, mind, health

    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_12_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
     sớm
    0.49
    δ
    0.49
    ために
    0.49
     daya
    0.48
     bắt
    0.47
     thuế
    0.47
     meydana
    0.46
     advocated
    0.46
     diagon
    0.45
     disgust
    0.45
    POSITIVE LOGITS
    ille
    0.52
     ป
    0.51
     Colonel
    0.48
     улице
    0.47
    innen
    0.47
    argeon
    0.47
     Pepper
    0.46
     BBQ
    0.46
    rimin
    0.46
     chestnut
    0.45
    Activations Density 0.000%

    No Known Activations