© 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. 3428
    Prev
    Next
    INDEX
    Explanations

    MODE, Shell, talk, bukkits, LENGTH

    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
    س
    1.97
    ю
    1.83
    es
    1.74
    n
    1.70
    ки
    1.69
    нд
    1.61
     kazan
    1.59
    𝘰
    1.56
    т
    1.56
    та
    1.54
    POSITIVE LOGITS
    دی
    1.77
     anharmonic
    1.76
     takeover
    1.75
     এদিকে
    1.71
    好了
    1.61
    鹏
    1.61
    ▌
    1.61
    রি
    1.61
    ۰۰
    1.60
     প্রথমেই
    1.58
    Activations Density 0.000%

    No Known Activations