© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47665
    Prev
    Next
    INDEX
    Explanations

    assistant

    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_10_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
     are
    0.87
    4
    0.73
    0
    0.71
    人都
    0.63
    :
    0.63
    6
    0.62
    еру
    0.59
    助理
    0.58
     clotting
    0.57
     :
    0.56
    POSITIVE LOGITS
    odus
    0.66
     الجنوب
    0.66
     Në
    0.66
     Δε
    0.64
    jeni
    0.64
    ját
    0.64
     fundamento
    0.64
    ವಿಧ
    0.64
    on
    0.63
     النوع
    0.63
    Activations Density 0.014%

    No Known Activations