© 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-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 5887
    Prev
    Next
    INDEX
    Explanations

    export default

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    ম্ব
    1.58
     lidar
    1.54
    时候
    1.52
    важа
    1.47
     baryons
    1.43
    相続
    1.43
    ב
    1.43
     factura
    1.40
     ưu
    1.40
     micrographs
    1.39
    POSITIVE LOGITS
    за
    1.47
    s
    1.42
    sı
    1.42
    lide
    1.41
    lung
    1.41
    ্ড
    1.35
    buri
    1.34
    ্ট
    1.34
    uire
    1.33
    ের
    1.32
    Activations Density 0.002%

    No Known Activations