© 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. 2729
    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
    ∂
    1.96
    пись
    1.76
    ed
    1.75
    ɦ
    1.65
    ة
    1.65
    |।
    1.64
     bijection
    1.63
    .-\
    1.60
    ش
    1.56
    ليم
    1.56
    POSITIVE LOGITS
    os
    1.99
    𝑑
    1.82
     Ovaj
    1.79
     Jeżeli
    1.76
    𝑐
    1.66
    ிட்ட
    1.65
    খ্যা
    1.63
    いろんな
    1.63
     éventuellement
    1.62
    𝑢
    1.61
    Activations Density 0.000%

    No Known Activations