© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140945
    Prev
    Next
    INDEX
    Explanations

    above positions or altitude

    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_12_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
    لا
    0.57
    له
    0.55
     Solar
    0.55
     Sun
    0.54
     sun
    0.54
     ৷
    0.52
     Tatsache
    0.50
     finans
    0.50
    ↵↵↵
    0.49
     Sunshine
    0.49
    POSITIVE LOGITS
    graduation
    0.53
    最初に
    0.53
     കണ്ടെത്ത
    0.52
    endpoints
    0.52
    èrent
    0.51
     chọn
    0.50
     үз
    0.50
    最初は
    0.50
    uses
    0.49
    ucc
    0.49
    Activations Density 0.054%

    No Known Activations