© 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
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3270
    Prev
    Next
    INDEX
    Explanations

    links following punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    ה
    3.59
    ا
    3.54
    a
    3.23
    া
    2.98
    к
    2.83
    ੀ
    2.76
    ル
    2.73
    ן
    2.71
     rağmen
    2.71
    んばんは
    2.65
    POSITIVE LOGITS
    с
    2.87
     الَّذ
    2.61
    .'”
    2.52
    dır
    2.47
    сного
    2.45
    𝘻
    2.42
    值
    2.41
    𝐝
    2.41
    ۱
    2.38
    ′,
    2.37
    Activations Density 0.060%

    No Known Activations