© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30599
    Prev
    Next
    INDEX
    Explanations

    days in a year

    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_40_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
     ख
    0.40
    多的
    0.38
    很多
    0.38
     nM
    0.37
     الكثير
    0.36
     Mohan
    0.36
    景色
    0.36
     كثير
    0.36
    जनबी
    0.36
    cm
    0.35
    POSITIVE LOGITS
     días
    0.38
    אות
    0.38
     lengths
    0.38
     days
    0.37
     दाता
    0.37
    ၡ
    0.36
     toss
    0.36
     Tó
    0.36
     Knox
    0.35
    ifle
    0.35
    Activations Density 0.003%

    No Known Activations