© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15067
    Prev
    Next
    INDEX
    Explanations

    capital adequacy

    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_13_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
    ᐉ
    0.55
     Maugin
    0.55
    没人
    0.54
    روی
    0.51
    بی
    0.50
    ចែកចាយ
    0.50
     Kendall
    0.50
     Função
    0.50
    癤
    0.49
    iffent
    0.49
    POSITIVE LOGITS
     when
    0.59
     quando
    0.52
     conten
    0.51
     cuando
    0.51
     cas
    0.50
     когато
    0.49
    When
    0.49
     solution
    0.49
     stock
    0.48
     statistically
    0.47
    Activations Density 0.007%

    No Known Activations