© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40292
    Prev
    Next
    INDEX
    Explanations

    van, Van, Von Neumann

    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_11_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
    ى
    0.64
    ティ
    0.61
    ै
    0.59
    '
    0.57
     asegur
    0.57
    ル
    0.56
    ේ
    0.55
    n
    0.54
     '+':
    0.54
     Animals
    0.53
    POSITIVE LOGITS
    ความเป็น
    0.60
     مفهوم
    0.54
     मोठे
    0.53
     должности
    0.52
    ozer
    0.51
    hk
    0.50
    arov
    0.50
     δυ
    0.50
     spheres
    0.49
     berbentuk
    0.49
    Activations Density 0.002%

    No Known Activations