© 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. 256937
    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
    set
    0.96
    */
    0.89
    raw
    0.87
    error
    0.86
    p
    0.86
    help
    0.86
    cli
    0.84
    version
    0.83
    picker
    0.82
    constants
    0.81
    POSITIVE LOGITS
     arsenic
    1.19
     Hindustan
    1.15
     Trojans
    1.11
     debts
    1.05
     Citibank
    1.05
     Ore
    1.04
     नेहरू
    1.02
     erc
    1.02
    ostock
    1.00
    羋
    0.99
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.