© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87803
    Prev
    Next
    INDEX
    Explanations

    Sihanoukville, tigers, Kahanamoku statue, Miso

    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
     હજાર
    0.70
    ।
    0.70
    الی
    0.66
    لین
    0.66
     موسی
    0.66
    ین
    0.65
    asilkan
    0.65
    efeller
    0.64
    ン
    0.64
    ।]
    0.63
    POSITIVE LOGITS
     on
    0.76
    EP
    0.71
    OS
    0.66
    ра
    0.66
    EST
    0.66
    ET
    0.63
     It
    0.62
     These
    0.61
    v
    0.59
    re
    0.58
    Activations Density 0.000%

    No Known Activations