© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 201235
    Prev
    Next
    INDEX
    Explanations

    des

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    روع
    0.40
     rou
    0.39
     comprise
    0.38
    ້ອຍ
    0.38
    Jun
    0.38
     rub
    0.37
     ノー
    0.37
    ع
    0.37
    閏
    0.37
    uí
    0.37
    POSITIVE LOGITS
    rias
    0.47
    み
    0.41
    ्ला
    0.40
     ben
    0.40
    वरील
    0.39
    ria
    0.39
     MI
    0.39
    啸
    0.39
     amit
    0.39
    CMI
    0.38
    Activations Density 0.002%

    No Known Activations