© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175199
    Prev
    Next
    INDEX
    Explanations

    CUDA errors

    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_50_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
    annulation
    0.45
    [][
    0.44
    [][]
    0.39
    েরা
    0.38
    स्तर
    0.37
     spe
    0.36
     Spe
    0.36
     instructive
    0.36
    ún
    0.36
     Ann
    0.36
    POSITIVE LOGITS
    몰
    0.40
     forerunner
    0.39
     declare
    0.37
     sus
    0.37
     gk
    0.37
     mơ
    0.36
     forefront
    0.36
     tane
    0.35
     Pearce
    0.35
    бет
    0.35
    Activations Density 0.001%

    No Known Activations