© 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. 121511
    Prev
    Next
    INDEX
    Explanations

    health and wellbeing topics

    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
     needles
    0.54
    針
    0.51
    clinic
    0.50
    针
    0.50
     clinic
    0.49
     clinics
    0.47
     Diagnosis
    0.47
     Clinic
    0.47
    Diagnosis
    0.46
     needle
    0.46
    POSITIVE LOGITS
     arch
    0.43
    ᱧ
    0.39
     permainan
    0.38
     Sling
    0.38
     Pengh
    0.38
     sling
    0.37
     дове
    0.37
     doctrines
    0.37
    дове
    0.37
     doctrine
    0.36
    Activations Density 0.029%

    No Known Activations