© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 790
    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_2_width_16k_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
    ος
    0.99
    ار
    0.96
    ع
    0.93
    ن
    0.92
    ER
    0.91
    ный
    0.91
    ر
    0.89
    ის
    0.88
     vem
    0.85
    یت
    0.84
    POSITIVE LOGITS
    ्ठा
    0.98
    ernetes
    0.94
     enlightened
    0.92
     overturn
    0.91
     whack
    0.90
    webView
    0.90
     doux
    0.87
    ‖</
    0.87
    Какие
    0.87
    сай
    0.86
    Activations Density 0.110%

    No Known Activations