© 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. 3054
    Prev
    Next
    INDEX
    Explanations

    running code commands

    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
    ه
    1.81
    на
    1.67
     временем
    1.62
    дето
    1.58
    ع
    1.58
     jee
    1.55
    cS
    1.55
     deus
    1.53
    샵
    1.50
    勞
    1.49
    POSITIVE LOGITS
    administered
    1.78
    multiplier
    1.70
    ()=>{
    1.70
    \},
    1.58
    eking
    1.57
    یثیت
    1.57
     runApp
    1.55
     implications
    1.54
    tfidf
    1.54
     scraped
    1.53
    Activations Density 0.000%

    No Known Activations