© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38271
    Prev
    Next
    INDEX
    Explanations

    enabling harm or positive outcomes

    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_11_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
    凖
    0.66
    adığı
    0.63
    ompok
    0.61
    uhà
    0.59
    ו
    0.59
    poetry
    0.58
    Петербург
    0.58
    bih
    0.58
    MINE
    0.58
    扞
    0.58
    POSITIVE LOGITS
     band
    0.71
     agua
    0.71
     le
    0.68
     silica
    0.62
    4
    0.61
     fuel
    0.60
     long
    0.59
     d
    0.59
     club
    0.59
     length
    0.58
    Activations Density 0.003%

    No Known Activations