© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6873
    Prev
    Next
    INDEX
    Explanations

    matplotlib.pyplot as plt

    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
    ্স
    2.35
     действий
    2.30
    '/
    2.16
    ាច់
    2.14
    ЕЛ
    1.98
    ă
    1.93
     hubungan
    1.89
    )?.
    1.87
    స్‌
    1.85
    خدام
    1.82
    POSITIVE LOGITS
    𝑑
    2.43
    𝑠
    2.03
    췌
    1.81
    ১৮
    1.77
    𝑡
    1.76
    ियोजना
    1.74
    ingale
    1.73
     ACA
    1.70
    𝑏
    1.68
    다음
    1.68
    Activations Density 0.005%

    No Known Activations