© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175632
    Prev
    Next
    INDEX
    Explanations

    national geographic/world history/cnn travel

    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_20_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
    王
    0.47
    views
    0.44
     Additionally
    0.44
    ढ़े
    0.42
     পড়েছে
    0.42
        
    0.41
    主角
    0.40
    捏
    0.40
     المهم
    0.40
     এছাড়া
    0.40
    POSITIVE LOGITS
     gimnas
    0.42
    ্কা
    0.41
    ítása
    0.41
     deshalb
    0.41
    Wen
    0.41
     sœur
    0.40
     boas
    0.40
    islava
    0.39
     rhet
    0.39
    itando
    0.39
    Activations Density 0.001%

    No Known Activations