© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127892
    Prev
    Next
    INDEX
    Explanations

    reflow function

    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_3_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
    é
    0.85
    í
    0.75
     flavonoids
    0.74
    á
    0.70
     glimpses
    0.65
    ่า
    0.63
     imperfections
    0.61
     detalles
    0.60
    ק
    0.58
     tiempos
    0.58
    POSITIVE LOGITS
    다
    0.72
    elijke
    0.68
    ed
    0.67
     can
    0.66
    。
    0.66
    electric
    0.65
    ുള്ള
    0.63
    પ
    0.62
    el
    0.61
     derde
    0.61
    Activations Density 0.000%

    No Known Activations