© 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. 127079
    Prev
    Next
    INDEX
    Explanations

    metabolic pathways and reactions

    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
    сем
    0.41
     आगाज
    0.40
    Quan
    0.39
     μυ
    0.39
    évaluation
    0.37
    intended
    0.37
    航
    0.37
    방
    0.36
     démarrage
    0.36
    ăm
    0.36
    POSITIVE LOGITS
     KE
    0.46
     கே
    0.42
     metabolic
    0.42
     Cushing
    0.40
     whispering
    0.40
    鳕
    0.38
     Schuster
    0.38
     Metabolic
    0.38
    KE
    0.38
    突出
    0.37
    Activations Density 0.001%

    No Known Activations