© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13576
    Prev
    Next
    INDEX
    Explanations

    doesn't know

    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_13_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
    ные
    0.27
    ៈ
    0.23
    ناها
    0.23
    тится
    0.22
    景色
    0.22
    кты
    0.21
    няется
    0.21
    ป
    0.21
    тивные
    0.21
    جهزة
    0.20
    POSITIVE LOGITS
    ;">
    0.24
     بواسطة
    0.24
    .).
    0.23
     oleh
    0.22
     wala
    0.21
    ordi
    0.21
     did
    0.21
     במש
    0.21
    ord
    0.20
    ارڈ
    0.20
    Activations Density 0.046%

    No Known Activations