© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15908
    Prev
    Next
    INDEX
    Explanations

    code endings

    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_34_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
    >\
    0.41
     সত্ব
    0.36
     जाप
    0.36
     достав
    0.35
     Итак
    0.34
     genital
    0.34
     attent
    0.34
     නමුත්
    0.34
    caster
    0.33
     oliv
    0.33
    POSITIVE LOGITS
     Wirtschafts
    0.40
     FON
    0.39
     lần
    0.38
    आम
    0.37
     Folk
    0.36
    幹
    0.35
     φορά
    0.34
    Named
    0.34
     aufgenommen
    0.33
    MONG
    0.33
    Activations Density 0.063%

    No Known Activations