© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11880
    Prev
    Next
    INDEX
    Explanations

    age or role followed by name

    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_13_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
    世界
    0.27
    ოლო
    0.25
    側に
    0.25
     Civilization
    0.25
    Tempo
    0.25
     Architecture
    0.24
     Biennale
    0.24
    食
    0.23
    文化
    0.23
     Tf
    0.23
    POSITIVE LOGITS
    𝗱
    0.30
    ge
    0.29
     mereka
    0.28
     ఏర్ప
    0.27
     கெல்வின்
    0.27
     ابراہیم
    0.27
    𝙨
    0.27
     वर्णन
    0.26
     ကျွန်
    0.26
    ího
    0.25
    Activations Density 0.013%

    No Known Activations