© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9485
    Prev
    Next
    INDEX
    Explanations

    define

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    epart
    0.71
    lysninger
    0.67
     Rok
    0.66
     सामील
    0.65
     साग
    0.65
    orh
    0.63
    >("
    0.62
    䀘
    0.61
    抔
    0.61
    遷
    0.60
    POSITIVE LOGITS
     defined
    3.95
     define
    3.77
    defined
    3.62
    定义
    3.41
     Defined
    3.38
     defines
    3.37
    define
    3.37
    Defined
    3.24
    定義
    3.24
    Define
    3.22
    Activations Density 0.533%

    No Known Activations