© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33517
    Prev
    Next
    INDEX
    Explanations

    climate change and behavior changes

    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_40_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
    科技
    0.41
     glycerin
    0.39
    塁
    0.37
     scienza
    0.37
     Wissenschaft
    0.37
    谕
    0.35
    lenül
    0.35
    Ꮫ
    0.35
    ちは
    0.34
     GUI
    0.34
    POSITIVE LOGITS
    changes
    0.79
     changes
    0.76
     Changes
    0.75
     perubahan
    0.73
    变化
    0.71
     تغییر
    0.69
    Changes
    0.68
     mudanças
    0.68
     changing
    0.68
     Changing
    0.67
    Activations Density 0.053%

    No Known Activations