© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51213
    Prev
    Next
    INDEX
    Explanations

    I was

    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_31_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
     Ru
    0.31
     stories
    0.30
     Stories
    0.30
     apparent
    0.29
    ワン
    0.29
     র
    0.29
    Stories
    0.29
    胃
    0.28
    陵
    0.28
     PLANS
    0.28
    POSITIVE LOGITS
     sprinkle
    0.35
     refin
    0.35
    จัดการ
    0.34
    ੌਰ
    0.33
    isko
    0.33
    รอ
    0.33
    artic
    0.32
    َف
    0.32
    ohex
    0.32
    وسف
    0.32
    Activations Density 0.007%

    No Known Activations