© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 27063
    Prev
    Next
    INDEX
    Explanations

    organic molecules and chemical formulas

    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_10_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
    اة
    0.61
    is
    0.54
    ز
    0.54
    isn
    0.54
     ballistic
    0.49
     severely
    0.47
    ميل
    0.47
    enal
    0.47
    ဒ
    0.47
    <0xBA>
    0.47
    POSITIVE LOGITS
    </h2>
    0.61
    ll
    0.55
     That
    0.52
    争取
    0.51
     Commod
    0.51
    莊
    0.50
     ആശയ
    0.49
     Entom
    0.49
    ls
    0.48
     Toward
    0.48
    Activations Density 0.054%

    No Known Activations