© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12134
    Prev
    Next
    INDEX
    Explanations

    Nurse, hygienist, paralegal professions

    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_13_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
    acco
    0.56
    ered
    0.55
    0
    0.54
    nig
    0.54
    igham
    0.53
    oline
    0.51
    cken
    0.51
    runken
    0.51
    ità
    0.50
    nies
    0.50
    POSITIVE LOGITS
     새로운
    0.59
    asamb
    0.55
     защото
    0.55
     философ
    0.55
    நபியே
    0.54
     لأنه
    0.53
    悖
    0.53
    ᠶ
    0.53
     nové
    0.52
     Ори
    0.52
    Activations Density 0.015%

    No Known Activations