© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59037
    Prev
    Next
    INDEX
    Explanations

    Indian empires and dynasties

    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_11_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
    ⏜
    0.53
    dwm
    0.50
    dengan
    0.50
    ᴍ
    0.49
    ټبال
    0.49
     सेवाओं
    0.49
    ڎ
    0.49
    луйста
    0.49
     фонбет
    0.48
     עם
    0.47
    POSITIVE LOGITS
    ول
    0.49
    EN
    0.47
    use
    0.46
    </h3>
    0.43
    었
    0.42
    up
    0.41
    anas
    0.41
     ganas
    0.40
     strlen
    0.40
     up
    0.40
    Activations Density 0.006%

    No Known Activations