© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136033
    Prev
    Next
    INDEX
    Explanations

    perform their job duties

    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
    Christmas
    0.36
    ACP
    0.35
    🟣
    0.35
    ={},
    0.35
    好处
    0.35
     対応
    0.34
    Chat
    0.33
     physiologique
    0.33
    citealt
    0.33
    阡
    0.33
    POSITIVE LOGITS
     своей
    0.61
     pracy
    0.61
     work
    0.60
     कार्य
    0.57
     práce
    0.56
     работы
    0.55
     trabajo
    0.54
     работу
    0.54
     swoich
    0.54
     lavoro
    0.53
    Activations Density 0.109%

    No Known Activations