© 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. 36341
    Prev
    Next
    INDEX
    Explanations

    back pain

    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
     trap
    0.15
     slay
    0.14
     experiment
    0.14
    *
    0.14
     philosophical
    0.14
     Arctic
    0.13
    ad
    0.13
     BAR
    0.13
     sea
    0.13
    era
    0.13
    POSITIVE LOGITS
    <0xB5>
    0.17
    ഇ
    0.17
    iciência
    0.15
     İng
    0.15
    ﯽ
    0.15
     doenças
    0.14
     consiste
    0.14
     trong
    0.14
    ність
    0.14
     tâche
    0.14
    Activations Density 0.001%

    No Known Activations