© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 147439
    Prev
    Next
    INDEX
    Explanations

    German 'und'

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     Theorems
    0.38
    ᴍ
    0.35
     জেনে
    0.35
     ''){
    0.34
     ∗
    0.34
    (^
    0.34
     constructs
    0.33
    Thats
    0.33
     Qi
    0.32
    Mathematics
    0.32
    POSITIVE LOGITS
     und
    0.57
    und
    0.49
     con
    0.40
    UND
    0.39
     plight
    0.39
    unda
    0.38
     ።
    0.38
    Und
    0.38
     UND
    0.37
    🗳
    0.36
    Activations Density 0.000%

    No Known Activations