© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36367
    Prev
    Next
    INDEX
    Explanations

    airports and universities

    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
    לחמת
    0.44
    maschinen
    0.39
     የ
    0.38
     የስ
    0.36
     اجرای
    0.35
    ˌ
    0.35
    galactos
    0.34
    মিল
    0.33
    བ་
    0.33
    ceptible
    0.33
    POSITIVE LOGITS
    ֗
    0.42
     نہیں۔
    0.40
     menging
    0.36
    leton
    0.34
     இல்லை
    0.34
    ‌లు
    0.34
    कहां
    0.34
     നിന്ന്
    0.33
    िफिकेट
    0.33
     duniya
    0.33
    Activations Density 0.044%

    No Known Activations