© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 178451
    Prev
    Next
    INDEX
    Explanations

    multilingual questions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    贵
    1.61
    貴
    1.50
     귀
    1.45
     quý
    1.19
    귀
    1.17
     senhor
    1.12
     noble
    1.00
    贵的
    0.95
     தங்கள்
    0.92
    noble
    0.89
    POSITIVE LOGITS
    ftl
    0.37
    Connor
    0.37
    త్రి
    0.36
    Gro
    0.36
     ∞
    0.35
     htons
    0.35
    ∞
    0.35
    GAG
    0.34
    Artists
    0.34
     Tomcat
    0.34
    Activations Density 0.003%

    No Known Activations