© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 194600
    Prev
    Next
    INDEX
    Explanations

    United States of America

    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_9_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
    engkap
    0.53
    '
    0.50
     there
    0.50
     张
    0.50
     fin
    0.49
     https
    0.49
    ja
    0.48
     aw
    0.48
    up
    0.48
     using
    0.48
    POSITIVE LOGITS
    م
    0.54
     mechanisms
    0.52
    منا
    0.51
    hams
    0.46
    مول
    0.46
     democracies
    0.46
    高于
    0.46
    extra
    0.46
    opportunities
    0.45
    ردم
    0.45
    Activations Density 0.000%

    No Known Activations