© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3806
    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
    JLabel
    1.39
    matic
    1.35
    }`
    1.34
    ᅮ
    1.33
    ം
    1.31
    emente
    1.31
    вич
    1.30
    assertEquals
    1.28
     NSError
    1.28
    isering
    1.28
    POSITIVE LOGITS
    ूर्ण
    1.71
    そも
    1.55
    ্ম্ম
    1.44
    此
    1.38
     endowed
    1.37
    থ
    1.33
    깎
    1.32
    ுகிறார்கள்
    1.31
    weist
    1.30
    ۱۳
    1.30
    Activations Density 0.068%

    No Known Activations