© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88821
    Prev
    Next
    INDEX
    Explanations

    EasyJet

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ות
    0.73
    ने
    0.70
    ات
    0.70
    ัง
    0.67
    টি
    0.66
    льных
    0.63
    лянчук
    0.63
    ৯
    0.63
     iki
    0.60
    ünde
    0.59
    POSITIVE LOGITS
    o
    0.85
    It
    0.77
    ו
    0.74
    I
    0.72
    been
    0.69
    They
    0.68
     পড়িল
    0.68
    á
    0.67
     quinoa
    0.65
     था
    0.64
    Activations Density 0.001%

    No Known Activations