© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 257397
    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
     NSObject
    1.25
    占比
    1.25
    står
    1.22
     warriors
    1.21
     endast
    1.18
    篪
    1.17
     failing
    1.17
     bästa
    1.17
     claire
    1.16
     dupatta
    1.16
    POSITIVE LOGITS
    x
    1.08
    зи
    1.00
    subTest
    0.98
    쪼
    0.96
    tan
    0.96
    ່
    0.96
    да
    0.95
    బ
    0.94
    ನಲ್ಲಿ
    0.94
    甫
    0.92
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.