© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196763
    Prev
    Next
    INDEX
    Explanations

    type checking and error handling

    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_27_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
     frei
    0.40
    ція
    0.40
    Freq
    0.37
    [];
    0.37
     emissions
    0.37
    Dept
    0.37
     émissions
    0.37
     [];
    0.36
    ([]);
    0.36
     lumi
    0.36
    POSITIVE LOGITS
     كيف
    0.39
     సంగీ
    0.39
     elegante
    0.39
    美しい
    0.39
     PhoneNumber
    0.39
     ухуд
    0.39
     какое
    0.39
     Handwriting
    0.38
     करवाने
    0.38
     Linguistics
    0.38
    Activations Density 0.000%

    No Known Activations