© 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-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 917
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    fprintf
    2.40
    ร์
    2.39
    ′,
    2.38
    า
    2.17
    খ
    2.08
    াপ
    2.00
     жизнью
    1.98
    ″
    1.93
    ️⃣
    1.90
    quot
    1.87
    POSITIVE LOGITS
    此之外
    2.30
    н
    2.06
    steak
    1.98
    ν
    1.97
    itesi
    1.92
    يء
    1.91
    𝗶
    1.89
    ل
    1.87
    ៉
    1.85
    nä
    1.85
    Activations Density 0.027%

    No Known Activations