© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231556
    Prev
    Next
    INDEX
    Explanations

    language classification

    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_6_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
    ㅋ
    1.11
    u
    1.05
    को
    0.92
    인이
    0.92
    ą
    0.89
    ł
    0.88
    ຂອງ
    0.85
    q
    0.84
    지
    0.83
    ai
    0.83
    POSITIVE LOGITS
    ↵↵
    1.14
    1.00
    3
    0.90
    ال
    0.86
     jums
    0.81
    ECH
    0.79
    ну
    0.77
    ур
    0.77
    няется
    0.77
     sajana
    0.77
    Activations Density 0.003%

    No Known Activations