© 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. 3271
    Prev
    Next
    INDEX
    Explanations

    #define followed by hardware identifiers

    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
    ו
    1.49
    これで
    1.49
    ụ
    1.46
    ه
    1.45
    o
    1.41
    Hình
    1.39
    Comma
    1.38
     dator
    1.38
     Confira
    1.36
     leto
    1.35
    POSITIVE LOGITS
     Hell
    1.39
    ет
    1.35
     Ais
    1.32
     marginLeft
    1.31
     ""),
    1.29
     grievances
    1.29
    ت
    1.28
     FOM
    1.27
     Journalist
    1.27
    تری
    1.26
    Activations Density 0.001%

    No Known Activations