© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28596
    Prev
    Next
    INDEX
    Explanations

    web scrapped, settings, build, created model

    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
    贝尔
    0.43
    undet
    0.41
     अश
    0.36
    ровал
    0.36
     Cough
    0.36
     Gine
    0.35
     artères
    0.35
    扎
    0.35
     Yale
    0.34
    zag
    0.34
    POSITIVE LOGITS
     حبي
    0.40
     принцип
    0.37
     faster
    0.36
    வுக்கு
    0.36
    Watching
    0.35
     verder
    0.34
     explos
    0.34
    વાહી
    0.34
     Runtime
    0.34
     lúc
    0.34
    Activations Density 0.054%

    No Known Activations