© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9632
    Prev
    Next
    INDEX
    Explanations

    say "of"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     of
    1.00
     different
    0.82
     của
    0.82
     diferentes
    0.81
     Different
    0.77
     diferente
    0.76
     של
    0.75
    ㅏ
    0.72
    ของ
    0.71
     oi
    0.71
    POSITIVE LOGITS
     ثلاثة
    0.79
     पांच
    0.66
     তিন
    0.66
     ثلاثه
    0.64
     ત્રણ
    0.62
     خمس
    0.62
     five
    0.61
     तीन
    0.59
    ళ్లు
    0.58
    five
    0.58
    Activations Density 0.027%

    No Known Activations