© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201199
    Prev
    Next
    INDEX
    Explanations

    my, his, their

    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_12_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
    )
    0.63
     Banner
    0.49
    чі
    0.49
     September
    0.48
     Boston
    0.48
     brevity
    0.48
     Twitter
    0.48
    ו
    0.48
    ান
    0.47
     Article
    0.47
    POSITIVE LOGITS
     generación
    0.60
    ⚤
    0.59
     இணைப்பு
    0.54
    镓
    0.54
    టర్
    0.54
     конструкция
    0.54
     actualización
    0.53
    инг
    0.52
     شود
    0.51
     asociación
    0.51
    Activations Density 0.001%

    No Known Activations