© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60438
    Prev
    Next
    INDEX
    Explanations

    astrophotography and camera gear

    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_11_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
     bis
    0.61
    ProxyAgent
    0.57
     в
    0.56
    ompany
    0.56
    за
    0.55
    5
    0.55
     were
    0.54
    да
    0.54
     waren
    0.54
    ianza
    0.53
    POSITIVE LOGITS
    Diabetes
    0.69
     arrhythmias
    0.62
     diabetics
    0.61
    整形
    0.57
     Diabetes
    0.56
     carbohydrates
    0.55
     moul
    0.55
     bowls
    0.53
    ศิลป
    0.52
    壷
    0.52
    Activations Density 0.013%

    No Known Activations