© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200298
    Prev
    Next
    INDEX
    Explanations

    ware, earthenware, glassware, silverware

    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_6_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
    ak
    1.12
    С
    1.09
    ud
    1.05
    ors
    1.05
    Ml
    1.05
           
    1.02
    ol
    1.02
    आई
    1.01
    و
    0.99
    ill
    0.98
    POSITIVE LOGITS
    える
    0.98
    ાન
    0.97
    缴纳
    0.93
     paintbrush
    0.88
    ವಾಗಿ
    0.87
     trusty
    0.86
    지로
    0.86
    ジナル
    0.85
    리로
    0.84
     ہوگی
    0.84
    Activations Density 0.000%

    No Known Activations