© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    4. 4221
    Prev
    Next
    INDEX
    Explanations

    non- preceded by hyphen

    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_39_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
    Non
    0.70
     Non
    0.64
     non
    0.63
     NON
    0.58
    non
    0.54
    NON
    0.52
     नॉन
    0.50
    非
    0.48
     非
    0.46
     nonEmpty
    0.44
    POSITIVE LOGITS
    ôts
    0.38
     ومت
    0.36
    ISTAN
    0.35
     Approximately
    0.35
     ayrıca
    0.35
    amps
    0.34
     إجراء
    0.34
    mateurs
    0.33
    ariş
    0.33
    ждения
    0.33
    Activations Density 0.004%

    No Known Activations