© 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. 206428
    Prev
    Next
    INDEX
    Explanations

    home visits and Nurse visits

    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
     secretos
    0.40
     Controllers
    0.39
    巽
    0.38
     Estoy
    0.37
    刷
    0.35
     //=>
    0.35
     চেন
    0.35
    Beta
    0.34
    ʲ
    0.34
    Exper
    0.34
    POSITIVE LOGITS
     visiting
    0.80
     Visiting
    0.79
    Visiting
    0.74
    訪
    0.69
    訪問
    0.68
     방문
    0.68
     Visits
    0.66
     visited
    0.65
     visita
    0.64
     visits
    0.63
    Activations Density 0.000%

    No Known Activations