© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110070
    Prev
    Next
    INDEX
    Explanations

    disguise

    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_2_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
    на
    1.37
    도
    1.24
    و
    1.23
    ا
    1.13
    ма
    1.02
    もら
    1.02
    ని
    0.99
    在
    0.98
    다
    0.94
     in
    0.93
    POSITIVE LOGITS
    )。
    0.87
    中国
    0.84
    本
    0.82
    ৫
    0.82
    st
    0.82
    defin
    0.80
    多少
    0.79
    تها
    0.79
    ري
    0.78
    ر
    0.78
    Activations Density 0.001%

    No Known Activations