© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 235406
    Prev
    Next
    INDEX
    Explanations

    Philippines and international topics

    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_32_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
    
    0.41
    ledge
    0.39
    etin
    0.38
    øre
    0.37
     遊ん
    0.37
    ας
    0.37
    vaccinated
    0.37
    slots
    0.37
     वस्त्र
    0.37
    ira
    0.36
    POSITIVE LOGITS
    禍
    0.39
    祸
    0.37
    시키는
    0.36
     जैसा
    0.35
     deprecated
    0.35
    墜
    0.35
     external
    0.35
     внешний
    0.35
    訳
    0.35
     popup
    0.34
    Activations Density 0.000%

    No Known Activations