© 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. 91988
    Prev
    Next
    INDEX
    Explanations

    religious traditions and holidays

    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
    탠
    0.61
    ーパー
    0.61
     soutenir
    0.57
    ਰ
    0.55
    olf
    0.54
    له
    0.54
    etaan
    0.54
    ر
    0.54
     エン
    0.53
    un
    0.52
    POSITIVE LOGITS
     कहा
    0.60
     nói
    0.52
     phút
    0.48
     dwRes
    0.48
     hunt
    0.47
    kannya
    0.47
     जाधव
    0.47
     çünkü
    0.47
     useCallback
    0.47
    डर
    0.46
    Activations Density 0.000%

    No Known Activations