© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 259839
    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
     Parque
    1.34
    autiful
    1.28
    cean
    1.26
    ٢
    1.16
     Prothorax
    1.16
     Quadrupèdes
    1.15
    istical
    1.14
    conom
    1.14
     duties
    1.14
    cych
    1.12
    POSITIVE LOGITS
    ਸੀਂ
    1.10
    順
    1.08
    on
    1.05
    RELL
    1.04
    grove
    1.03
    VERY
    0.98
     restructured
    0.97
    loud
    0.96
     narrowing
    0.96
    NORMAL
    0.93
    Activations Density 0.000%

    No Known Activations