© 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. 196876
    Prev
    Next
    INDEX
    Explanations

    but these or this

    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
     frü
    0.36
     ([]
    0.36
     Hd
    0.35
    瑤
    0.35
     ஈ
    0.34
     mezzo
    0.34
     otherwise
    0.34
    才能
    0.33
     انگیز
    0.33
    ൯
    0.33
    POSITIVE LOGITS
    solete
    0.40
     llegan
    0.39
    ्रोत
    0.39
     علامه
    0.38
     Wildlife
    0.38
     larval
    0.37
     अनावश्यक
    0.37
     अशुभ
    0.36
    ujesz
    0.36
     येतो
    0.36
    Activations Density 0.001%

    No Known Activations