© 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. 134430
    Prev
    Next
    INDEX
    Explanations

    used traditionally for medicinal purposes

    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
    古代
    0.45
    galax
    0.40
    }}^{*
    0.37
     설명을
    0.37
    ancient
    0.36
     monolayers
    0.35
     древ
    0.35
    覤
    0.35
    واكب
    0.35
    愎
    0.35
    POSITIVE LOGITS
     medicinal
    0.46
     herbal
    0.45
     Medicinal
    0.42
     medicina
    0.41
     bastard
    0.40
     Esa
    0.40
     Herbal
    0.39
    Medic
    0.39
     Alu
    0.38
     bern
    0.38
    Activations Density 0.004%

    No Known Activations