© 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
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 59005
    Prev
    Next
    INDEX
    Explanations

    hotel staff

    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_11_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
    ១
    0.52
    पी
    0.51
     পদ্ধতি
    0.51
    1
    0.50
    ่
    0.49
     undergraduates
    0.49
    1
    0.49
    eger
    0.48
    ━━━━
    0.48
     universities
    0.47
    POSITIVE LOGITS
    computed
    0.59
     који
    0.56
    ダル
    0.55
    as
    0.55
     alcune
    0.54
     lequel
    0.52
    לים
    0.52
     pomoći
    0.52
     İlç
    0.52
     apoi
    0.52
    Activations Density 0.000%

    No Known Activations