© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 420
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    时候
    1.86
    k
    1.61
    னம்
    1.26
    g
    1.25
     sino
    1.24
    ابی
    1.23
     pres
    1.23
    e
    1.20
    Доброго
    1.20
    ون
    1.20
    POSITIVE LOGITS
     positrons
    1.54
    tır
    1.54
    ต์
    1.52
     convict
    1.50
    न्त्र
    1.47
    MESSAGE
    1.47
    evil
    1.47
    ་་
    1.45
    रोवर
    1.44
    elementary
    1.44
    Activations Density 0.626%

    No Known Activations