© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164424
    Prev
    Next
    INDEX
    Explanations

    json structure delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_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
     নিম্নলিখিত
    0.36
    ́
    0.36
     следующие
    0.36
    SANITIZE
    0.33
    зан
    0.33
    ா
    0.33
    ριο
    0.32
     оде
    0.32
    座
    0.31
    स्त
    0.31
    POSITIVE LOGITS
     circ
    0.39
    ']*
    0.38
     partout
    0.37
     تعال
    0.36
    ജീവ
    0.36
     textColor
    0.35
    чак
    0.35
    ccccn
    0.34
     feita
    0.34
    OUG
    0.33
    Activations Density 0.003%

    No Known Activations