© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86673
    Prev
    Next
    INDEX
    Explanations

    active form, pharmaceutical ingredient, healthy lifestyles

    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_3_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
    นี่
    0.66
    िज
    0.64
    นั่ง
    0.61
    چنین
    0.61
    ി
    0.61
    .
    0.60
    ש
    0.59
    ləşdir
    0.57
    ো
    0.57
    지
    0.56
    POSITIVE LOGITS
    на
    0.94
    ре
    0.78
    在
    0.73
    ни
    0.71
     در
    0.67
    á
    0.63
    к
    0.62
    wür
    0.62
    રી
    0.61
    ١
    0.60
    Activations Density 0.036%

    No Known Activations