© 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. 1219
    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
     zwar
    3.00
    ../
    2.79
    ている
    2.60
     dabei
    2.57
    م
    2.50
    Ꮙ
    2.44
     bisschen
    2.43
     bicara
    2.41
    ので
    2.39
    wa
    2.30
    POSITIVE LOGITS
    ar
    3.08
    ক
    3.04
    yrs
    2.98
     encompassing
    2.97
    ्राफी
    2.93
    ת
    2.86
     impressive
    2.75
     Personally
    2.72
    iterations
    2.71
     coincidence
    2.70
    Activations Density 0.043%

    No Known Activations