© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205568
    Prev
    Next
    INDEX
    Explanations

    nth Fibonacci number

    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_20_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
     дз
    0.27
     HOST
    0.26
     formulario
    0.25
     よ
    0.25
     funcionario
    0.25
     прото
    0.25
     جوا
    0.25
    頊
    0.24
     இ
    0.24
    ходы
    0.24
    POSITIVE LOGITS
    tochrome
    0.24
    American
    0.24
    langen
    0.24
    സ്തു
    0.24
     loca
    0.24
     burgl
    0.24
    years
    0.24
    Tennessee
    0.23
    وي
    0.23
    美国的
    0.23
    Activations Density 0.001%

    No Known Activations