© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 1929
    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
     रिप्रेजेंट
    0.49
     ย
    0.43
    ար
    0.42
    নং
    0.39
     ม
    0.39
     maupun
    0.39
     रिप्रे
    0.38
    ᄆ
    0.37
     medida
    0.37
    ពួកគេ
    0.37
    POSITIVE LOGITS
     included
    0.45
     mottled
    0.43
     only
    0.43
     inclusion
    0.42
     one
    0.42
     purified
    0.42
    ؟
    0.41
     muster
    0.41
    inclusion
    0.41
     bleached
    0.40
    Activations Density 0.223%

    No Known Activations