© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 258798
    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_10_width_262k_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
     donna
    1.46
     DRAM
    1.39
     fortemente
    1.39
     fist
    1.34
     добиться
    1.33
    𝚔
    1.32
     возле
    1.32
    exponent
    1.32
     GAO
    1.29
     Taq
    1.29
    POSITIVE LOGITS
    r
    1.14
    l
    1.12
    t
    1.11
    mits
    1.11
     obstante
    1.10
    o
    1.10
    a
    1.07
     illustration
    1.05
    ン
    1.03
    हों
    1.00
    Activations Density 0.000%

    No Known Activations