© 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. 11959
    Prev
    Next
    INDEX
    Explanations

    Arab Spring countries

    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
     sorrow
    0.55
    ி
    0.50
     morbid
    0.49
     school
    0.49
     ?
    0.48
     graduate
    0.47
    еро
    0.46
     кто
    0.46
     σχ
    0.46
     класси
    0.45
    POSITIVE LOGITS
     modelu
    0.52
    Established
    0.50
     Unterstüt
    0.50
     okvir
    0.49
    𝚣
    0.49
     étab
    0.48
    Пер
    0.48
    nsec
    0.48
    žení
    0.47
     வழிப
    0.47
    Activations Density 0.004%

    No Known Activations