© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 152022
    Prev
    Next
    INDEX
    Explanations

    进行

    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_59_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    の上
    0.50
     five
    0.42
     personal
    0.41
     eight
    0.39
     dei
    0.39
     three
    0.38
     six
    0.38
    ან
    0.38
     Zen
    0.38
     내
    0.38
    POSITIVE LOGITS
    为
    0.82
    為
    0.78
    selecting
    0.68
    appending
    0.64
     Transforming
    0.64
     Selecting
    0.61
    Integrating
    0.60
     Integrating
    0.60
    Converting
    0.60
    Selecting
    0.60
    Activations Density 0.001%

    No Known Activations