© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228267
    Prev
    Next
    INDEX
    Explanations

    exynos processors or sin

    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_6_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
     as
    1.15
    o
    1.05
     letzten
    0.93
     bacteria
    0.92
    ว
    0.91
    e
    0.90
    ם
    0.88
    u
    0.87
     dunia
    0.86
    r
    0.86
    POSITIVE LOGITS
    T
    1.20
    りと
    0.88
    N
    0.84
    Gew
    0.83
    Dé
    0.81
    S
    0.80
    {
    0.79
    liel
    0.78
    Č
    0.77
    Пер
    0.77
    Activations Density 0.000%

    No Known Activations