© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9974
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     қи
    0.39
     yielded
    0.38
    沙
    0.37
     pav
    0.36
    猀
    0.36
     yield
    0.36
     hydroxy
    0.36
     quenching
    0.36
     хрони
    0.36
    ⌒
    0.36
    POSITIVE LOGITS
     married
    1.71
     Married
    1.55
    married
    1.53
    Married
    1.50
     marry
    1.05
     marries
    1.05
     unmarried
    0.96
     MARRI
    0.96
     menikah
    0.95
     বিবাহ
    0.89
    Activations Density 0.002%

    No Known Activations