© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2483
    Prev
    Next
    INDEX
    Explanations

    Smithsonian Magazine topics: science, history, 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_40_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
     popular
    0.43
    េ
    0.41
    大众
    0.38
    Popular
    0.38
    popular
    0.38
     Popular
    0.36
     популярных
    0.35
     populer
    0.33
     популяр
    0.33
     populaire
    0.32
    POSITIVE LOGITS
    準
    0.31
     CNBC
    0.30
    zij
    0.30
    ober
    0.29
    佰
    0.29
     وزی
    0.29
    ubh
    0.29
     Staub
    0.29
     CNN
    0.29
    ziele
    0.29
    Activations Density 0.001%

    No Known Activations