© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172731
    Prev
    Next
    INDEX
    Explanations

    objects with mass

    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
    ]));
    0.43
     البيانات
    0.43
    ASCII
    0.43
    பு
    0.43
     Psychology
    0.42
     BMW
    0.41
    чними
    0.41
     مي
    0.40
    數
    0.40
     ה
    0.39
    POSITIVE LOGITS
    °-
    0.46
     impide
    0.46
    샀
    0.45
     सर्दी
    0.45
    NavItem
    0.44
    dancer
    0.44
     élect
    0.43
    ῳ
    0.43
     whipping
    0.43
     acond
    0.42
    Activations Density 0.001%

    No Known Activations