© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3769
    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
    স
    2.28
    場合
    2.27
    ✱
    2.13
    ج
    2.13
    WebElement
    2.06
    ➖➖
    2.06
    ため
    2.04
     averaged
    2.01
    یثیت
    2.00
    い
    1.98
    POSITIVE LOGITS
    ים
    2.04
    ю
    1.77
    つまり
    1.72
    ла
    1.69
     کوچ
    1.58
    ண்டி
    1.57
     overloading
    1.57
    可以将
    1.57
     tive
    1.57
    astype
    1.55
    Activations Density 0.018%

    No Known Activations