© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180678
    Prev
    Next
    INDEX
    Explanations

    trabajaban | ARTIFICIAL | department | your

    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_24_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
     сва
    0.34
    ฌ
    0.32
    쎌
    0.32
     Favre
    0.31
    POINTS
    0.30
     deslig
    0.30
     DPS
    0.30
     있
    0.30
    सेस
    0.29
    Downward
    0.29
    POSITIVE LOGITS
    សូម
    0.35
     nincs
    0.34
     ഏറ്റവും
    0.34
    ún
    0.33
    orted
    0.33
    hela
    0.33
     இதுவரை
    0.33
    anch
    0.32
    based
    0.32
     فلسطینی
    0.32
    Activations Density 0.000%

    No Known Activations