© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 123
    Prev
    Next
    INDEX
    Explanations

    Santa Valley Islands Provence

    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
    ﺹ
    0.35
     quies
    0.35
    pert
    0.35
     мет
    0.35
     parties
    0.34
    ﹋
    0.34
     getUsersBy
    0.34
     quét
    0.34
     fal
    0.33
     heels
    0.33
    POSITIVE LOGITS
     Ventura
    0.50
     Camar
    0.46
     concept
    0.39
    鍮
    0.38
    Vent
    0.37
     Chum
    0.36
     ম্যাজিস্ট্রেট
    0.36
     Newbury
    0.35
    concept
    0.35
     Ox
    0.34
    Activations Density 0.001%

    No Known Activations