© 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. 2671
    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
    속
    1.79
     Į
    1.68
    METHODS
    1.61
    ually
    1.50
    noindent
    1.48
    另一方面
    1.47
    ∫
    1.47
    hereafter
    1.47
    ">';
    1.46
     있는
    1.46
    POSITIVE LOGITS
    에
    1.92
    ี
    1.83
    től
    1.79
    őtt
    1.78
     وهو
    1.69
    બાદ
    1.65
     kunne
    1.64
     positrons
    1.63
    त
    1.62
     volts
    1.61
    Activations Density 0.003%

    No Known Activations