© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 88699
    Prev
    Next
    INDEX
    Explanations

    type in

    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_11_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
     economica
    0.54
    )_{(
    0.51
    мих
    0.51
     svm
    0.50
    ષ
    0.50
     ле
    0.50
     দুর্ভিক্ষ
    0.50
     फेव
    0.49
    )^
    0.49
    BufferedReader
    0.49
    POSITIVE LOGITS
    পত্র
    0.47
    ewood
    0.46
    loro
    0.45
     customer
    0.45
    elivery
    0.45
    otch
    0.44
    ning
    0.43
     compliance
    0.43
    loading
    0.43
    使用者
    0.42
    Activations Density 0.000%

    No Known Activations