© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214641
    Prev
    Next
    INDEX
    Explanations

    real, realisto, realistas

    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_5_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
     be
    1.58
     that
    1.42
    {
    1.42
     to
    1.41
     a
    1.39
     i
    1.32
     as
    1.30
     an
    1.28
     e
    1.27
     v
    1.25
    POSITIVE LOGITS
    もら
    1.16
    ामध्ये
    1.13
    ično
    1.06
    ти
    1.05
     splike
    1.05
    ו
    1.05
     функция
    1.04
    ا
    1.04
    m
    1.01
     obten
    0.99
    Activations Density 0.007%

    No Known Activations