© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8920
    Prev
    Next
    INDEX
    Explanations

    what is happening?

    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_13_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
    un
    0.43
    ut
    0.42
    Gent
    0.41
    ir
    0.39
    (
    0.39
    ac
    0.39
    •
    0.38
    ot
    0.37
    ff
    0.37
    Щ
    0.37
    POSITIVE LOGITS
     percorso
    0.34
     replicating
    0.33
     groot
    0.32
     کاسینو
    0.32
     résolution
    0.32
     roaring
    0.31
     diagnosing
    0.31
     buffering
    0.31
     munk
    0.31
     celery
    0.31
    Activations Density 0.141%

    No Known Activations