© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115271
    Prev
    Next
    INDEX
    Explanations

    Atmospheric, delivery, scan, graph, rona, scapes

    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_27_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
     Dune
    0.38
     superiors
    0.37
     विराजमान
    0.35
     продукции
    0.35
     nü
    0.35
     Reproduced
    0.34
     Vectors
    0.34
    ु
    0.34
     प्रबंधन
    0.34
     Superior
    0.33
    POSITIVE LOGITS
    岧
    0.40
     fondamentali
    0.40
    medio
    0.38
     ump
    0.38
    Dichloro
    0.37
    ▢
    0.36
    عرِّف
    0.36
    ereur
    0.36
     Fmat
    0.35
     രണ്ട
    0.35
    Activations Density 0.021%

    No Known Activations