© 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. 45398
    Prev
    Next
    INDEX
    Explanations

    prosecution management party

    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
    ্রী
    0.55
     было
    0.55
     अपनी
    0.54
     быть
    0.52
     perten
    0.52
     belong
    0.51
     长
    0.51
    ्राट
    0.51
    ওয়ার্ড
    0.51
     Кы
    0.50
    POSITIVE LOGITS
    تون
    0.54
    Glucose
    0.50
    熱
    0.48
    ancienne
    0.45
     décider
    0.45
    莓
    0.44
    im
    0.43
    ap
    0.43
     Initiatives
    0.42
    承包
    0.42
    Activations Density 0.013%

    No Known Activations