© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7626
    Prev
    Next
    INDEX
    Explanations

    negative emotions like upset, tired, sad, angry

    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_39_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
     cationic
    0.37
     شخصی
    0.34
    icillin
    0.33
     main
    0.32
    車種
    0.32
    |<
    0.31
    蚀
    0.31
     anionic
    0.31
    isotopes
    0.30
    িকার
    0.30
    POSITIVE LOGITS
     উনি
    0.37
    噫
    0.34
    Joh
    0.33
    Rio
    0.33
     Reflection
    0.32
    yi
    0.32
     Challenge
    0.32
     Joh
    0.31
    Johann
    0.31
     constantly
    0.31
    Activations Density 0.090%

    No Known Activations