© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 11882
    Prev
    Next
    INDEX
    Explanations

    explanation of why

    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_13_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
     kerana
    0.58
     lymphatiques
    0.54
     गर्ल्स
    0.51
     Ў
    0.50
     μετά
    0.49
     ਲਈ
    0.48
     서비스
    0.48
    کین
    0.48
    “)
    0.47
     ポイント
    0.47
    POSITIVE LOGITS
    rap
    0.40
    apro
    0.39
    Graduate
    0.39
    comp
    0.39
    導
    0.38
     habil
    0.38
    вед
    0.38
     complejo
    0.38
    اب
    0.38
    moder
    0.38
    Activations Density 0.081%

    No Known Activations