© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32531
    Prev
    Next
    INDEX
    Explanations

    offensive language

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ଳ
    0.42
    ्लाई
    0.39
    就是在
    0.39
    न्नत
    0.39
     protrusion
    0.38
     ഞാൻ
    0.38
     retinol
    0.38
     coss
    0.37
     رون
    0.37
     nunc
    0.37
    POSITIVE LOGITS
    tha
    0.56
    х
    0.54
    хло
    0.51
    va
    0.50
    hwa
    0.47
    THA
    0.47
    uhu
    0.46
    wa
    0.45
    ieh
    0.45
    huy
    0.45
    Activations Density 0.049%

    No Known Activations