© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49389
    Prev
    Next
    INDEX
    Explanations

    core

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    核
    2.03
     kernel
    1.87
     Kernel
    1.77
     kernels
    1.76
     nucleus
    1.73
     핵
    1.73
     ядер
    1.71
     Nucle
    1.69
     核
    1.68
     nuclear
    1.67
    POSITIVE LOGITS
    ্লিষ্ট
    0.39
    लांग
    0.39
    说说
    0.39
     കോ
    0.38
    कॉ
    0.38
    鱷
    0.38
    Ĭ
    0.37
     कॉ
    0.36
    袴
    0.36
    杠
    0.35
    Activations Density 0.005%

    No Known Activations