© 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. 259792
    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
     खाम
    1.04
     esperar
    1.03
    y
    1.01
    meshgrid
    1.00
    ej
    0.99
     pretty
    0.96
    yue
    0.94
    توى
    0.90
     Watering
    0.90
    eol
    0.90
    POSITIVE LOGITS
     vật
    1.25
     czemu
    1.25
    Microsoft
    1.24
    ᑕ
    1.22
    Faucet
    1.22
    Для
    1.21
    teenth
    1.20
    Dengan
    1.19
    送料無料
    1.18
    ivity
    1.18
    Activations Density 0.000%

    No Known Activations