© 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. 78317
    Prev
    Next
    INDEX
    Explanations

    dining reservations

    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
    🎢
    0.43
     Warrior
    0.37
    웃
    0.36
     Intens
    0.36
     Incl
    0.35
     Scholars
    0.35
    MEs
    0.34
     inclined
    0.33
     woody
    0.33
     Us
    0.33
    POSITIVE LOGITS
    ته
    0.32
    自動車
    0.31
     خودرو
    0.31
     автомобі
    0.31
     dazzling
    0.30
    を実現
    0.30
    鮮
    0.30
     শাসক
    0.30
    醂
    0.30
     агент
    0.29
    Activations Density 0.002%

    No Known Activations