© 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. 91240
    Prev
    Next
    INDEX
    Explanations

    Sustainable Development Goals (SDG)

    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
    if
    0.57
    ’
    0.56
    എ
    0.55
    loc
    0.53
     ল
    0.49
    ای
    0.49
    खे
    0.49
    azir
    0.48
    enaar
    0.48
    피
    0.47
    POSITIVE LOGITS
     cancelling
    0.60
     cancellation
    0.59
     spongy
    0.58
     stamping
    0.57
    🥯
    0.56
     rude
    0.55
     polymorphic
    0.55
     navigational
    0.55
     cancelled
    0.54
     softer
    0.54
    Activations Density 0.001%

    No Known Activations