© 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. 16062
    Prev
    Next
    INDEX
    Explanations

    Kubernetes deployment commands and concepts

    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
    itumor
    0.42
    ใบ
    0.40
     листь
    0.39
     ใบ
    0.38
     Elvis
    0.37
    ~.,
    0.37
    발
    0.36
     તો
    0.36
    Би
    0.36
     Grac
    0.36
    POSITIVE LOGITS
    sticker
    0.40
    ாண்ட
    0.38
    britann
    0.37
     gesetz
    0.37
     Waterfront
    0.37
     карто
    0.36
     म्हणतात
    0.36
    restricted
    0.36
    ாங்க
    0.36
     खुली
    0.35
    Activations Density 0.015%

    No Known Activations