© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130996
    Prev
    Next
    INDEX
    Explanations

    month or months

    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_25_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
     अपना
    0.38
     Constitución
    0.38
     diverses
    0.38
    ेश
    0.37
     diversas
    0.37
     сотрудник
    0.37
     ย
    0.36
     Aqui
    0.36
     Sistema
    0.36
     مواقع
    0.35
    POSITIVE LOGITS
    тив
    0.45
    illor
    0.42
     solltest
    0.42
    瞽
    0.41
     albumen
    0.40
    ഗണ
    0.39
     musst
    0.38
    텐츠
    0.37
     கம
    0.37
    bücher
    0.37
    Activations Density 0.001%

    No Known Activations