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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136550
    Prev
    Next
    INDEX
    Explanations

    non-english words

    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
     Tekh
    0.40
    融入
    0.40
    顧
    0.40
    顾
    0.39
    驅
    0.39
     permanece
    0.38
    ற்றிய
    0.38
     पाई
    0.38
     রহিম
    0.38
     sust
    0.38
    POSITIVE LOGITS
    зі
    0.41
     ইহা
    0.37
     хан
    0.36
    寞
    0.36
    жая
    0.36
     красный
    0.35
     глава
    0.35
    Jackie
    0.35
    깅
    0.34
    ኼ
    0.34
    Activations Density 0.000%

    No Known Activations