© 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. 1295
    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
    ENING
    1.31
    ا
    1.29
    х
    1.26
     spanning
    1.21
    нтов
    1.16
    ва
    1.16
    InteropServices
    1.09
     불구하고
    1.09
    Ibid
    1.08
    ردم
    1.07
    POSITIVE LOGITS
     damn
    1.27
    irradiated
    1.24
     groe
    1.21
    大丈夫
    1.12
    Πα
    1.11
    !\!\
    1.10
     enda
    1.08
    款
    1.07
    ように
    1.06
    sofar
    1.05
    Activations Density 0.005%

    No Known Activations