© 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. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 367
    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_12_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
     only
    0.17
     or
    0.16
    ,
    0.16
    only
    0.16
     agricultural
    0.16
     network
    0.15
     trimmed
    0.15
     collected
    0.14
     new
    0.14
     oder
    0.14
    POSITIVE LOGITS
    бычно
    0.17
    瘫
    0.16
     İyi
    0.16
    Token
    0.16
    㙋
    0.16
     biasing
    0.16
     Phương
    0.16
     Hình
    0.16
     प्रशंसा
    0.16
     Při
    0.16
    Activations Density 3.313%

    No Known Activations