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

    Neuronpedia

    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. 260023
    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
     scripture
    1.21
    jų
    1.19
     शेड्यूल
    1.16
     scriptures
    1.15
    édez
    1.15
     região
    1.14
    qtd
    1.13
    澳
    1.13
     hẹn
    1.11
     sauvegarde
    1.10
    POSITIVE LOGITS
    n
    1.36
    м
    1.32
    مع
    1.27
     annoying
    1.22
    el
    1.16
    塔尔
    1.14
    ят
    1.10
    ″
    1.10
    tr
    1.10
    ل
    1.10
    Activations Density 0.000%

    No Known Activations