© 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. 1751
    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
     subtlet
    1.62
    比べて
    1.56
     lbl
    1.52
    ﮟ
    1.51
    विद्यालय
    1.49
    ઓ
    1.49
    बारक
    1.49
    ,}$
    1.47
    jeto
    1.46
    hā
    1.44
    POSITIVE LOGITS
    я
    1.89
    ும்
    1.83
    缛
    1.78
    те
    1.77
    й
    1.70
     hecho
    1.57
    які
    1.54
    ៌
    1.53
    ი
    1.51
    мери
    1.49
    Activations Density 0.018%

    No Known Activations