© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63394
    Prev
    Next
    INDEX
    Explanations

    numbers in other languages

    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_46_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
    ంటి
    0.43
    ৩২
    0.38
    ध्याय
    0.36
    واء
    0.35
    ंथ
    0.35
    ㄻ
    0.35
    三百
    0.34
     જન્મ
    0.34
    KeyboardButton
    0.34
    叁
    0.34
    POSITIVE LOGITS
     ۵
    0.57
    五
    0.53
     ५
    0.52
     पाच
    0.50
     пять
    0.50
     cinque
    0.50
    ５
    0.50
     पांच
    0.49
     ৫
    0.49
     ۶
    0.47
    Activations Density 0.026%

    No Known Activations