© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124696
    Prev
    Next
    INDEX
    Explanations

    Kenyan, KenKen, Kenshin, Kenji

    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_3_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
    )
    0.95
    _
    0.86
    in
    0.85
    >
    0.82
    =
    0.76
    u
    0.72
    ه
    0.72
    V
    0.71
    ic
    0.69
    ,
    0.67
    POSITIVE LOGITS
    سی
    0.68
    <unused56>
    0.61
     இருக்கலாம்
    0.59
    நபியே
    0.59
     beber
    0.57
     आजाद
    0.56
     Ам
    0.56
     délais
    0.56
    ระหว่าง
    0.55
    ಾರಿ
    0.55
    Activations Density 0.000%

    No Known Activations