© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 238579
    Prev
    Next
    INDEX
    Explanations

    React useState hook

    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_32_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
     ashes
    0.37
     gi
    0.36
     ``
    0.36
    䔉
    0.35
     Фонбет
    0.35
    菜
    0.34
     منظور
    0.34
    }`;
    0.33
     rejection
    0.33
     kapat
    0.33
    POSITIVE LOGITS
    祚
    0.40
    Texas
    0.39
    从此
    0.37
    纵
    0.36
    거나
    0.35
    新た
    0.35
    niac
    0.35
    京
    0.35
    Gif
    0.34
    綪
    0.34
    Activations Density 0.002%

    No Known Activations