© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 259668
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation in code or data

    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_10_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
    栝
    0.49
     São
    0.48
    ᄑ
    0.48
    iš
    0.47
     whirlpool
    0.46
    Điều
    0.45
    ਤਾ
    0.45
     أح
    0.45
     JavaBeans
    0.44
    }}=-\
    0.44
    POSITIVE LOGITS
     চর্
    0.47
     Nutzung
    0.44
    めで
    0.41
    ハード
    0.41
    文化的
    0.39
     attainment
    0.39
     dendritic
    0.39
    同时也
    0.39
    グ
    0.39
    引き続き
    0.39
    Activations Density 0.001%

    No Known Activations