© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45846
    Prev
    Next
    INDEX
    Explanations

    health and bodily function

    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_22_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
    स्करी
    0.15
     নক
    0.13
    ätter
    0.13
    కాల
    0.13
    Documents
    0.13
    campo
    0.13
    вища
    0.12
    钱
    0.12
     কাজ
    0.12
     נמצא
    0.12
    POSITIVE LOGITS
     Five
    0.16
    و
    0.15
     kinderg
    0.15
     thickly
    0.14
     Kids
    0.14
     childrens
    0.14
     Huskies
    0.14
     desactiv
    0.14
     deviations
    0.14
    yat
    0.14
    Activations Density 0.108%

    No Known Activations