© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92116
    Prev
    Next
    INDEX
    Explanations

    nightlife, dating, going out

    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
    ेक्ट
    0.66
    ৈত
    0.62
    慟
    0.61
    ל
    0.59
    模式
    0.57
     Therapeut
    0.57
    秫
    0.57
    ண்ட்
    0.56
    Чер
    0.56
    膩
    0.56
    POSITIVE LOGITS
    t
    0.89
    x
    0.73
    c
    0.64
    \
    0.64
    o
    0.61
    es
    0.61
     ups
    0.60
     springs
    0.58
    v
    0.57
     shops
    0.56
    Activations Density 0.035%

    No Known Activations