© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218287
    Prev
    Next
    INDEX
    Explanations

    code keywords and structure

    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_31_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
    闺
    0.35
    বেশী
    0.35
    ிழ
    0.34
     налого
    0.33
     dalje
    0.33
     Pensions
    0.33
    पृ
    0.33
    Рабо
    0.33
    閨
    0.32
    ឆ
    0.32
    POSITIVE LOGITS
     Акы
    0.32
    VertexBuffer
    0.32
     consecutivos
    0.32
    emarks
    0.30
    Wherever
    0.30
     consecutive
    0.30
     consecutively
    0.30
     whenever
    0.29
    忏
    0.29
     שכ
    0.29
    Activations Density 0.008%

    No Known Activations