© 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. 3520
    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
    𝖊
    3.13
    ্বরের
    2.96
    𝖔
    2.88
    en
    2.88
    てください
    2.79
    𝖑
    2.79
    𝖒
    2.76
    ेप
    2.67
    𝖎
    2.67
    ERING
    2.61
    POSITIVE LOGITS
    да
    3.68
    ang
    3.25
    u
    3.12
     మంది
    2.83
    ं
    2.55
    もら
    2.53
    ч
    2.53
    т
    2.53
    ন
    2.52
    د
    2.49
    Activations Density 0.038%

    No Known Activations