© 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. 92326
    Prev
    Next
    INDEX
    Explanations

    visit places

    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
    "
    0.87
     driving
    0.70
     addiction
    0.66
     diabetes
    0.64
     colle
    0.64
     problem
    0.63
     query
    0.61
     totality
    0.60
     path
    0.59
     liability
    0.59
    POSITIVE LOGITS
    ماً
    0.74
    ="|
    0.71
    ياً
    0.68
    adocia
    0.68
    𒇽
    0.64
     Valentina
    0.64
    asciiPanel
    0.63
     vergangenen
    0.63
     Firearms
    0.62
    🏺
    0.62
    Activations Density 0.002%

    No Known Activations