© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245670
    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_11_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
    স
    0.90
    бо
    0.86
    ástica
    0.86
    бі
    0.83
     بوا
    0.82
    тся
    0.80
    ώνει
    0.80
    িকার
    0.80
     ஒது
    0.79
    έρ
    0.77
    POSITIVE LOGITS
     satisfiable
    1.04
     hulls
    1.03
     apet
    0.93
     inflow
    0.93
    🚁
    0.91
     admissible
    0.90
     redox
    0.90
     :).
    0.89
     skyl
    0.89
     recordings
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.