© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1693
    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
    聩
    3.02
    ⎣
    3.01
     Kindly
    2.77
    imilar
    2.77
     copyrights
    2.73
    Луч
    2.72
    keycode
    2.72
    囩
    2.71
    freq
    2.71
    USION
    2.70
    POSITIVE LOGITS
    ю
    2.94
    at
    2.93
    ுள்ளார்
    2.91
    ے
    2.86
    an
    2.85
    +\
    2.83
    ينه
    2.66
     hark
    2.63
    zelfde
    2.54
    си
    2.50
    Activations Density 0.102%

    No Known Activations