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

    Neuronpedia

    Jacobian LensNEW
    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. 31455
    Prev
    Next
    INDEX
    Explanations

    Caribbean, West Indies, Africa

    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_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
     Datas
    0.42
     ម
    0.42
     concerto
    0.42
     az
    0.41
     Auro
    0.39
     autonomous
    0.38
     Autonomous
    0.38
     essay
    0.38
     come
    0.38
    ತ್ತ
    0.37
    POSITIVE LOGITS
    West
    0.77
     West
    0.70
    西
    0.52
     वेस्ट
    0.51
    पश्चिम
    0.50
     غرب
    0.47
     पश्चिम
    0.47
    পশ্চিম
    0.46
     WEST
    0.46
     ওয়েস্ট
    0.44
    Activations Density 0.021%

    No Known Activations