© 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
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 92139
    Prev
    Next
    INDEX
    Explanations

    reacting or response

    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
    à
    0.73
    ou
    0.64
     Seattle
    0.64
     À
    0.62
     Clo
    0.61
     PA
    0.60
     you
    0.59
     Y
    0.58
     SMC
    0.58
     Crom
    0.57
    POSITIVE LOGITS
     جلوگیری
    0.67
     نداشت
    0.64
    diabetes
    0.62
    VideoButton
    0.60
    datos
    0.60
     inicios
    0.60
     pengaturan
    0.59
     वेबसाइट
    0.58
    ामान्य
    0.57
    نین
    0.57
    Activations Density 0.000%

    No Known Activations