© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 333
    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
    𝐰
    3.27
    as
    3.13
    முறை
    2.93
    le
    2.93
    ist
    2.92
    𝐞
    2.92
    ों
    2.81
    త
    2.79
     pairwise
    2.78
    ない
    2.76
    POSITIVE LOGITS
     sıra
    2.78
    нка
    2.77
    است
    2.77
    ო
    2.76
     abiertos
    2.74
    letzt
    2.72
    нки
    2.71
     upravo
    2.69
    तरी
    2.67
     oxalic
    2.66
    Activations Density 0.078%

    No Known Activations