© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91223
    Prev
    Next
    INDEX
    Explanations

    time decay (theta)

    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
    glazed
    0.62
    rische
    0.62
    inationals
    0.61
    ل
    0.61
    phones
    0.59
    wegs
    0.57
    dropped
    0.57
    ވި
    0.57
    у
    0.57
    kým
    0.55
    POSITIVE LOGITS
    ।
    0.89
    。
    0.77
    م
    0.76
    。(
    0.73
    ם
    0.73
     ร
    0.69
     o
    0.68
     。
    0.68
     บ
    0.66
     {
    0.65
    Activations Density 0.001%

    No Known Activations