© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 258882
    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
     stuffing
    1.34
    ের
    1.33
     annuities
    1.32
     fairly
    1.27
    聿
    1.25
     Mediterranean
    1.24
     conter
    1.21
    瀞
    1.21
     tractors
    1.20
    Mediterranean
    1.19
    POSITIVE LOGITS
    art
    1.10
    il
    1.08
    stup
    1.03
    Trong
    1.02
    yr
    0.99
    i
    0.99
    ან
    0.99
    нули
    0.98
    のは
    0.95
    ilin
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.