© 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. 770
    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
    PlistBuddy
    2.80
     littered
    2.48
    
    2.31
     কথা
    2.29
    なり
    2.27
     flaw
    2.26
    डोर
    2.19
     заказа
    2.18
    ం
    2.17
     clav
    2.14
    POSITIVE LOGITS
    ോഗ്യ
    2.43
    नाइटेड
    2.37
    impanan
    2.29
    jTextField
    2.28
    πο
    2.25
    quisa
    2.15
    َا
    2.13
     uns
    2.12
    ل
    2.07
    מ
    2.07
    Activations Density 0.130%

    No Known Activations