© 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. 59030
    Prev
    Next
    INDEX
    Explanations

    datapad

    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
    л
    0.73
    ל
    0.70
    ल
    0.64
    я
    0.60
     letzte
    0.59
     l
    0.59
    ме
    0.59
    ї
    0.58
    хи
    0.57
    1
    0.55
    POSITIVE LOGITS
     براي
    0.71
     কষ্টের
    0.60
     ਮ
    0.60
    addData
    0.60
    arci
    0.59
    cheiden
    0.58
    ঁপ
    0.57
     smrti
    0.57
    sadpoetry
    0.55
     hogy
    0.55
    Activations Density 0.000%

    No Known Activations