© 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. 256955
    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
    tipo
    1.22
    да
    1.12
    кт
    1.01
    tip
    1.00
    можно
    0.99
    ᴗ
    0.98
    اشت
    0.97
    tried
    0.97
    tat
    0.96
    day
    0.95
    POSITIVE LOGITS
    ി
    1.41
     пище
    1.32
    ें
    1.29
     Headphones
    1.28
     Sneakers
    1.28
     Indices
    1.27
    පත්
    1.25
     Sensitivity
    1.24
     Insurance
    1.24
     Efforts
    1.24
    Activations Density 0.000%

    No Known Activations