© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 197356
    Prev
    Next
    INDEX
    Explanations

    is

    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_26_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
    ارا
    0.34
    inburgh
    0.33
    ോഷ്യ
    0.32
    روز
    0.32
    ラジオ
    0.32
     Idee
    0.31
     esperar
    0.30
    遌
    0.30
    igrants
    0.30
    チャレンジ
    0.29
    POSITIVE LOGITS
    स्तों
    0.35
     nitrification
    0.34
    izante
    0.32
    按钮
    0.31
     בת
    0.31
    ုံး
    0.31
     buttons
    0.30
     validType
    0.30
     button
    0.30
     بالت
    0.30
    Activations Density 0.014%

    No Known Activations