© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 69393
    Prev
    Next
    INDEX
    Explanations

    women

    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_46_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
    veys
    0.37
     Australians
    0.37
     통
    0.37
     leopards
    0.37
     Lib
    0.36
     LIB
    0.36
    通
    0.36
     nurses
    0.36
    ค
    0.35
    Freel
    0.35
    POSITIVE LOGITS
    िसोदिया
    0.40
    imgInit
    0.39
    ភ្ជាប់
    0.39
     declinations
    0.38
    >")
    0.38
    тено
    0.38
    Dequeue
    0.37
     গাঙ্গুল
    0.36
    ofy
    0.36
    τί
    0.36
    Activations Density 0.001%

    No Known Activations