© 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. 918
    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
     народу
    2.91
     potrebno
    2.84
     eerder
    2.83
     Então
    2.54
     déterminé
    2.53
     Será
    2.42
    к
    2.39
     необхідно
    2.39
     откуда
    2.37
     бы
    2.36
    POSITIVE LOGITS
    র
    2.91
    zonych
    2.81
    ことで
    2.76
    ל
    2.75
    स
    2.63
    UTICAL
    2.60
    adrenergic
    2.60
    𝓉
    2.56
    礡
    2.56
    in
    2.52
    Activations Density 0.439%

    No Known Activations