© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158788
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
     הראש
    1.26
    ן
    1.13
    ע
    1.08
     arrondi
    1.07
    1.05
    נ
    1.03
     ancien
    1.02
     In
    1.00
     éta
    1.00
     The
    1.00
    POSITIVE LOGITS
    ٣
    1.09
    ۳
    1.09
    ६
    1.07
    া
    1.06
    ۴
    1.06
    ३
    1.05
    3
    1.04
    日数
    1.02
    ى
    1.00
    ти
    0.98
    Activations Density 0.000%

    No Known Activations