© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 235725
    Prev
    Next
    INDEX
    Explanations

    thank goodness for

    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_25_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
     counterfeit
    0.25
     okaza
    0.23
    rukt
    0.22
     prem
    0.22
    adera
    0.22
    )^
    0.22
    १८४
    0.22
     indign
    0.22
    ron
    0.22
    rub
    0.22
    POSITIVE LOGITS
     catégorie
    0.29
     CQG
    0.28
    笫
    0.28
    狧
    0.28
     supérieures
    0.27
     ahorita
    0.27
     jolie
    0.27
     ತಯ
    0.27
    yming
    0.27
     ਤਾਂ
    0.27
    Activations Density 0.001%

    No Known Activations