© 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. 214861
    Prev
    Next
    INDEX
    Explanations

    filled with joy and everything

    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
     delays
    0.39
    授業
    0.39
    🚻
    0.38
     أيض
    0.37
     নিয়ত
    0.36
     Realt
    0.36
    ⋘
    0.36
    🏪
    0.36
     Beziehung
    0.35
    ĸ
    0.35
    POSITIVE LOGITS
    paque
    0.43
     proton
    0.38
    proton
    0.36
     diseñado
    0.36
    izons
    0.35
    Fail
    0.34
    rians
    0.34
    進
    0.34
    ouveau
    0.34
    torio
    0.34
    Activations Density 0.001%

    No Known Activations