© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1512
    Prev
    Next
    INDEX
    Explanations

    python code imports

    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_39_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
     Rohan
    0.35
    ழிவு
    0.33
    rebbe
    0.32
     Disk
    0.31
    >/</
    0.31
    मीर
    0.31
    𒄑
    0.31
     enzimas
    0.30
     Progressives
    0.30
    狲
    0.30
    POSITIVE LOGITS
     delay
    0.35
     Delay
    0.35
    DELAY
    0.33
    延
    0.32
    Delay
    0.31
     vacations
    0.31
    клю
    0.31
    ！！！！
    0.30
     Vacation
    0.30
    ：（
    0.30
    Activations Density 0.038%

    No Known Activations