© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121353
    Prev
    Next
    INDEX
    Explanations

    ironically or irony

    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_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Nuclear
    0.39
     gospodar
    0.37
     Nuclear
    0.37
     ಮೇಲೆ
    0.37
    核
    0.36
    onucle
    0.36
    obacillus
    0.36
    ogad
    0.35
    杈
    0.35
    ancha
    0.35
    POSITIVE LOGITS
     irony
    2.94
     ironic
    2.77
     iron
    2.20
    iron
    2.19
     Iron
    2.14
    Iron
    2.09
     ironically
    2.06
     IRON
    1.93
    IRON
    1.90
     Ironically
    1.71
    Activations Density 0.183%

    No Known Activations