© 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
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 2971
    Prev
    Next
    INDEX
    Explanations

    Pattern: common prefixes to suffixes and parentheticals

    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
    스
    2.02
    ır
    1.86
     sere
    1.76
    চরা
    1.68
     ocor
    1.66
     reasoning
    1.65
    ન
    1.65
    >}</
    1.64
     eloquently
    1.64
     অ্য
    1.62
    POSITIVE LOGITS
    or
    1.76
     Sicher
    1.70
    িশালী
    1.60
    chromedriver
    1.58
     darn
    1.57
    heaven
    1.54
    valueOf
    1.53
    ie
    1.52
    क
    1.51
     அதற்கு
    1.51
    Activations Density 0.000%

    No Known Activations