© 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. 3674
    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
    celikle
    1.76
    ₫
    1.75
    let
    1.73
    յ
    1.60
    kung
    1.60
    zin
    1.54
    fd
    1.51
     allons
    1.50
     スチール
    1.49
    ce
    1.49
    POSITIVE LOGITS
    en
    1.69
     prilikom
    1.68
    у
    1.67
    APPENDIX
    1.66
     што
    1.62
     inflicted
    1.61
    お
    1.57
    ال
    1.52
    ский
    1.49
    matic
    1.48
    Activations Density 0.002%

    No Known Activations