© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 9495
    Prev
    Next
    INDEX
    Explanations

    loss function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    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
    ﺤ
    2.02
    ﺭ
    1.97
    iors
    1.93
    を取得
    1.91
    nummer
    1.86
    jším
    1.81
    ação
    1.78
    jeet
    1.77
    ง
    1.72
     Đường
    1.70
    POSITIVE LOGITS
    м
    2.58
    ن
    2.41
    م
    2.39
    ية
    2.31
    ت
    2.16
    ే
    2.05
    ة
    2.00
    ת
    1.95
    ა
    1.91
    ع
    1.90
    Activations Density 0.015%

    No Known Activations