© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1498
    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
    нку
    1.46
    มี
    1.41
    ここ
    1.41
    一个
    1.41
    ্ধ্য
    1.36
    )$;
    1.36
    ج
    1.35
    全長
    1.35
    д
    1.33
    NAC
    1.33
    POSITIVE LOGITS
    stood
    1.75
    Į
    1.61
     rarity
    1.58
     Yorkers
    1.57
    वा
    1.49
    ఆ
    1.49
     Rupees
    1.45
    ﺮ
    1.45
    owało
    1.44
    ConsoleText
    1.44
    Activations Density 0.161%

    No Known Activations