© 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. 5010
    Prev
    Next
    INDEX
    Explanations

    keep an eye

    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
    atomic
    2.78
    ك
    2.74
    кт
    2.73
    অনে
    2.70
     Needless
    2.70
    flipped
    2.57
    tilde
    2.54
    ט
    2.53
    ंगाई
    2.52
    ت
    2.50
    POSITIVE LOGITS
    علی
    2.88
    ка
    2.65
    loh
    2.56
    реди
    2.51
    чної
    2.47
    نات
    2.41
    ї
    2.38
    یہ
    2.35
    ся
    2.34
    и
    2.34
    Activations Density 0.011%

    No Known Activations