© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15617
    Prev
    Next
    INDEX
    Explanations

    Johns Hopkins and University of Chicago

    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_15_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
    u
    0.54
     १८४
    0.53
    otricha
    0.52
    awsze
    0.52
    patx
    0.51
     ज्यामुळे
    0.50
     ပဲ
    0.50
    秏
    0.50
     Tạo
    0.49
    కోవడం
    0.49
    POSITIVE LOGITS
    2
    0.52
     management
    0.50
     manipulator
    0.49
     sider
    0.48
     navigation
    0.48
     reservation
    0.47
     resistance
    0.47
    航
    0.46
    Management
    0.46
     pillow
    0.45
    Activations Density 0.001%

    No Known Activations