© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89327
    Prev
    Next
    INDEX
    Explanations

    glued to screens or phones

    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
     Sprach
    0.63
     ছন্দ
    0.63
    емые
    0.62
     Robots
    0.62
     Pued
    0.61
     Branches
    0.60
    弦
    0.59
    త్య
    0.59
    চ্ছেন
    0.58
     বাঁধ
    0.58
    POSITIVE LOGITS
     tattha
    0.71
    t
    0.68
     yattha
    0.67
    net
    0.66
     patitth
    0.65
     adhipp
    0.61
     그대로
    0.61
     methamphetamine
    0.61
     огне
    0.61
    ak
    0.60
    Activations Density 0.001%

    No Known Activations