© 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. 679
    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
     bunyi
    1.87
    कृष्ण
    1.72
    짜
    1.70
    р
    1.67
    ল
    1.65
     kadar
    1.63
     pois
    1.60
    ﺩ
    1.60
     sinds
    1.60
    ar
    1.59
    POSITIVE LOGITS
    стта
    1.58
    se
    1.57
    ші
    1.55
    الع
    1.48
    یک
    1.46
     JTextField
    1.42
    عت
    1.41
    сть
    1.41
     Largest
    1.37
    ள்ளது
    1.37
    Activations Density 0.118%

    No Known Activations