© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175066
    Prev
    Next
    INDEX
    Explanations

    EU directives, funds, and European matters

    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_20_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
    ăţ
    0.43
    èg
    0.42
    hető
    0.40
     Pinto
    0.40
    ̝
    0.39
    uma
    0.39
    ác
    0.39
    ettre
    0.38
    asy
    0.38
    Тем
    0.38
    POSITIVE LOGITS
     Beziehung
    0.49
    フード
    0.40
     因
    0.39
     ৬৫
    0.39
    Xiaomi
    0.39
    歓
    0.39
     უ
    0.38
     textarea
    0.38
     nahezu
    0.38
    三次
    0.37
    Activations Density 0.001%

    No Known Activations