© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45200
    Prev
    Next
    INDEX
    Explanations

    stock photosimages & photos

    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_10_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
    ق
    0.55
     We
    0.49
     RAM
    0.45
     discrim
    0.45
     Smiths
    0.44
     Washington
    0.44
    ز
    0.42
     RATE
    0.42
    ى
    0.40
     specialise
    0.40
    POSITIVE LOGITS
    ran
    0.64
    cosx
    0.57
    nicu
    0.56
    ra
    0.55
    dl
    0.54
    gub
    0.54
    raa
    0.52
    itipi
    0.52
    咘
    0.52
    zhihu
    0.51
    Activations Density 0.000%

    No Known Activations