© 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. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 616
    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_12_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
    phic
    0.47
    _);
    0.45
    願
    0.44
     unsurprisingly
    0.43
    cest
    0.43
     Madness
    0.42
    তো
    0.42
    ってみ
    0.42
    Modification
    0.42
    ท์
    0.42
    POSITIVE LOGITS
     kullanılır
    0.46
    Rl
    0.39
    ˶
    0.39
     wykon
    0.39
     ऊपर
    0.39
     dwóch
    0.38
     kilku
    0.38
     chwili
    0.38
    κών
    0.38
    瓴
    0.38
    Activations Density 0.002%

    No Known Activations