© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161366
    Prev
    Next
    INDEX
    Explanations

    anything you have

    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_31_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
     trapez
    0.43
    汛
    0.41
     comments
    0.38
     describes
    0.36
    岁的
    0.36
    MB
    0.36
     प्रती
    0.36
    OV
    0.35
     confiar
    0.35
     climbed
    0.35
    POSITIVE LOGITS
    Vendor
    0.47
     Vendor
    0.44
     Vendors
    0.43
    磪
    0.40
     vendor
    0.39
    vendor
    0.38
     poised
    0.38
    找出
    0.36
     policías
    0.36
    öger
    0.36
    Activations Density 0.014%

    No Known Activations