© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261314
    Prev
    Next
    INDEX
    Explanations

    expressions of understatement

    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_22_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
    ＊
    0.43
    loven
    0.38
    gr
    0.37
     darn
    0.37
    咪
    0.37
    ringen
    0.37
     rink
    0.37
    ້
    0.37
    lev
    0.36
    ass
    0.36
    POSITIVE LOGITS
     gacchati
    0.45
     принципе
    0.41
     ዋና
    0.41
    Downward
    0.40
     sabbam
    0.40
     ena
    0.39
     controla
    0.38
     Goshen
    0.38
     создал
    0.38
     बनाता
    0.38
    Activations Density 0.001%

    No Known Activations