© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138731
    Prev
    Next
    INDEX
    Explanations

    anti-inflammatory and anxiety

    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_37_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
     olefin
    0.55
    olefin
    0.54
     olefins
    0.51
     alkene
    0.49
     unsaturated
    0.46
    烯
    0.46
     vinyl
    0.44
    unsaturated
    0.43
     alkenyl
    0.43
     alken
    0.42
    POSITIVE LOGITS
     fin
    0.39
     علیہ
    0.38
     Plain
    0.37
    ulti
    0.37
    liferation
    0.37
     behar
    0.37
    紮
    0.36
     glo
    0.36
     toot
    0.36
     blo
    0.36
    Activations Density 0.001%

    No Known Activations