© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4869
    Prev
    Next
    INDEX
    Explanations

    dust, dusty

    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_3_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
    िक
    3.27
    ش
    2.58
     dugout
    2.57
    dosage
    2.48
     parsley
    2.37
     exemplaire
    2.31
    य
    2.28
     পক্ষে
    2.28
    我认为
    2.26
     muffler
    2.25
    POSITIVE LOGITS
    ت
    3.32
    NESDAY
    2.43
     fact
    2.31
     језик
    2.15
    मारी
    2.05
    戙
    2.03
    ainte
    1.97
    টিশ
    1.96
    evším
    1.96
    টাইমস
    1.95
    Activations Density 0.061%

    No Known Activations