© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 43840
    Prev
    Next
    INDEX
    Explanations

    Methylation, Danvers, Bovet, Plainview

    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_3_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
     I
    0.81
    其他
    0.63
    言い
    0.60
     convincingly
    0.57
     manier
    0.56
     improv
    0.56
    厛
    0.55
     thư
    0.55
     commencer
    0.54
     لوبه
    0.54
    POSITIVE LOGITS
    ли
    0.87
     that
    0.81
    न
    0.79
     you
    0.74
    ant
    0.73
    ف
    0.72
    ang
    0.70
    ন
    0.70
    й
    0.69
    buyers
    0.68
    Activations Density 0.002%

    No Known Activations