© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177153
    Prev
    Next
    INDEX
    Explanations

    countries

    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
    Not in Any Lists

    No Comments

    Negative Logits
    
    0.39
    ovskii
    0.38
    ‌്
    0.38
    ்ப
    0.38
    ٔ
    0.37
     Pei
    0.37
    ਼
    0.37
     Michele
    0.36
     Dari
    0.36
    oteur
    0.36
    POSITIVE LOGITS
    WhiteBalance
    0.39
    ')->
    0.38
    нке
    0.36
    Wildlife
    0.36
    াবাদী
    0.36
     উৎপন্ন
    0.35
    '):
    0.35
    বরে
    0.35
     cruises
    0.34
     Cruises
    0.34
    Activations Density 0.008%

    No Known Activations