© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155234
    Prev
    Next
    INDEX
    Explanations

    'we' / 'wij' / 'wir'

    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_50_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
    鈞
    0.41
     mascot
    0.41
    த்திலிருந்து
    0.40
    蹄
    0.38
    Michael
    0.38
    무리
    0.37
     aur
    0.37
     AVLNode
    0.37
    钧
    0.37
    AUR
    0.36
    POSITIVE LOGITS
     Wend
    0.39
    ώσεις
    0.38
     Він
    0.37
    épendant
    0.36
    ົວ
    0.35
     WENO
    0.35
     restorations
    0.35
     salons
    0.35
     tén
    0.35
    რც
    0.34
    Activations Density 0.000%

    No Known Activations