© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27502
    Prev
    Next
    INDEX
    Explanations

    this is a big one!

    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_10_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
    ’
    0.91
    '
    0.69
     أس
    0.66
     Antônio
    0.64
    äl
    0.63
     Jealous
    0.62
     أساس
    0.61
    ك
    0.61
    腖
    0.61
     أق
    0.60
    POSITIVE LOGITS
    ائیں۔
    0.66
     발생하는
    0.63
     같이
    0.61
    евского
    0.60
     conclude
    0.59
     devra
    0.57
    clide
    0.57
    тинг
    0.57
    гим
    0.57
    ט
    0.57
    Activations Density 0.007%

    No Known Activations