© 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. 37442
    Prev
    Next
    INDEX
    Explanations

    WRONG or utopian

    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
    ER
    0.62
    ใช้
    0.54
    setup
    0.52
     তেলেভ
    0.52
    Business
    0.50
    Gravity
    0.49
    IE
    0.49
    ە
    0.48
    வ
    0.48
    Function
    0.48
    POSITIVE LOGITS
     stormed
    0.51
    یش
    0.50
     what
    0.49
     many
    0.49
     destroying
    0.48
    ્સ
    0.48
     spiritual
    0.47
     ital
    0.47
     offre
    0.47
     skis
    0.47
    Activations Density 0.000%

    No Known Activations