© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8104
    Prev
    Next
    INDEX
    Explanations

    stop loss management

    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
    ر
    3.31
    rn
    3.03
    ki
    2.66
    ate
    2.62
    rp
    2.55
    ӕ
    2.50
     того
    2.47
    బీ
    2.42
    Ln
    2.40
    ly
    2.38
    POSITIVE LOGITS
    一个
    2.72
     рода
    2.68
    щих
    2.65
    щую
    2.59
    щие
    2.57
    قه
    2.48
     расчет
    2.47
    率
    2.37
    щими
    2.37
     lensing
    2.37
    Activations Density 0.028%

    No Known Activations