© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4904
    Prev
    Next
    INDEX
    Explanations

    t-tests

    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_3_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
    était
    3.02
    いる
    2.87
    و
    2.52
    ities
    2.45
    යේ
    2.34
     adequada
    2.26
    est
    2.19
    ற்று
    2.14
    ৮
    2.13
    ษฐ
    2.12
    POSITIVE LOGITS
    𝗸
    3.55
    ง
    2.87
    le
    2.79
    이
    2.78
    నా
    2.76
    که
    2.61
    𝗔
    2.61
    これで
    2.56
    𝗣
    2.56
    োপাধ্যা
    2.55
    Activations Density 0.000%

    No Known Activations