© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 2147
    Prev
    Next
    INDEX
    Explanations

    amount of stuff

    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
    ỗi
    0.39
    amilton
    0.36
     type
    0.36
    lect
    0.35
     knots
    0.35
    ږئ
    0.35
    úc
    0.35
    ⃙
    0.35
    लेट्स
    0.34
     leaflet
    0.34
    POSITIVE LOGITS
    平成
    0.37
     Reddy
    0.37
     ສະ
    0.37
     составе
    0.37
     solve
    0.36
     পক্ষে
    0.35
     位
    0.35
     складі
    0.35
     esquerda
    0.35
     muu
    0.35
    Activations Density 0.004%

    No Known Activations