© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63840
    Prev
    Next
    INDEX
    Explanations

    short phrases and rhetorical questions

    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_41_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
    頨
    0.40
     margin
    0.38
    Artículo
    0.37
    बरी
    0.37
    苦
    0.37
     wry
    0.36
     Margin
    0.36
    ̩
    0.36
    无奈
    0.35
    坆
    0.35
    POSITIVE LOGITS
    세기
    0.40
    sqlite
    0.38
    遷移
    0.37
    帖
    0.37
    iological
    0.37
    ielsen
    0.35
     nesta
    0.35
     شكله
    0.35
     ziehen
    0.35
    Beng
    0.35
    Activations Density 0.001%

    No Known Activations