© 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. 1757
    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
    ्या
    0.93
    [](
    0.89
    া
    0.84
    лся
    0.83
    ா
    0.83
     Nakamura
    0.82
     ferv
    0.81
    LowerCase
    0.81
     sisi
    0.80
    ম্বা
    0.79
    POSITIVE LOGITS
     indem
    0.99
     pamoja
    0.97
    י
    0.95
     açısından
    0.93
     jazdy
    0.92
    𝐝
    0.91
    irrit
    0.90
    oos
    0.90
    ikke
    0.89
     açı
    0.88
    Activations Density 0.001%

    No Known Activations