© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 197258
    Prev
    Next
    INDEX
    Explanations

    Ecuador

    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_15_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
    ir
    0.69
    s
    0.69
    in
    0.65
    bner
    0.64
    ng
    0.63
    ed
    0.63
    nta
    0.62
    ine
    0.61
     những
    0.60
    r
    0.59
    POSITIVE LOGITS
    珽
    0.55
    Аль
    0.54
    Ци
    0.54
     Condo
    0.54
    자가
    0.50
     konkrét
    0.50
    郄
    0.50
     tortilla
    0.50
    Кто
    0.50
     Quantification
    0.50
    Activations Density 0.001%

    No Known Activations