© 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. 256603
    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
    ió
    1.11
     WITH
    1.08
    𝑙
    1.07
     admitting
    1.07
    𝑟
    1.05
     Admit
    1.04
    𝑑
    1.03
     этой
    1.02
    iu
    1.02
    inned
    1.01
    POSITIVE LOGITS
    чатку
    1.31
    פות
    1.27
     relativ
    1.17
    gerald
    1.15
    榔
    1.13
     pls
    1.09
     circunst
    1.09
     vali
    1.08
     protokol
    1.08
     verhindern
    1.06
    Activations Density 0.000%

    No Known Activations