© 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. 355
    Prev
    Next
    INDEX
    Explanations

    formula or function

    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
    crollView
    0.39
    তত্ব
    0.39
     voort
    0.35
    enclose
    0.35
     inwon
    0.33
    ূ
    0.33
     Maddox
    0.33
     cela
    0.33
    herd
    0.33
     Rees
    0.32
    POSITIVE LOGITS
     సై
    0.38
     나는
    0.38
     mo
    0.36
     रहिए
    0.34
    BEN
    0.34
     ブルー
    0.33
     또
    0.32
     అదే
    0.31
    នោះ
    0.31
    ná
    0.31
    Activations Density 0.132%

    No Known Activations