© 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. 2723
    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
    NN
    3.20
    י
    2.92
    তম
    2.81
    skoj
    2.79
    शील
    2.78
    myp
    2.65
    εκ
    2.62
    le
    2.59
     tad
    2.56
    ит
    2.55
    POSITIVE LOGITS
     względu
    4.14
    платно
    3.45
    för
    3.08
     sepen
    3.05
     fail
    2.95
    렵
    2.88
     regard
    2.87
     aucun
    2.85
    Ꮖ
    2.83
     Weiter
    2.81
    Activations Density 0.015%

    No Known Activations