© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41838
    Prev
    Next
    INDEX
    Explanations

    explaining why the original was incorrect

    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_22_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
    Herkese
    0.39
    脚本
    0.38
     соціа
    0.38
     सुकून
    0.38
     باوجود
    0.38
    瑆
    0.38
     وحدة
    0.37
    жли
    0.37
    ಲಾಗುತ್ತದೆ
    0.37
    Τα
    0.37
    POSITIVE LOGITS
    :
    0.54
     Was
    0.46
     gaze
    0.43
     petals
    0.42
    :");
    0.41
    ؟
    0.41
     Paint
    0.40
     painters
    0.40
     paint
    0.39
     Pet
    0.39
    Activations Density 0.014%

    No Known Activations