© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    4. 645
    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
    ה
    1.98
    вет
    1.81
     sempat
    1.75
    ي
    1.66
    ine
    1.66
    其
    1.57
    есть
    1.57
    י
    1.55
    ા
    1.54
     attenuate
    1.53
    POSITIVE LOGITS
     scap
    1.67
     tanned
    1.59
     pepp
    1.56
    𝓬
    1.52
    挛
    1.49
    میں
    1.42
    haired
    1.42
    hemy
    1.41
     rapport
    1.41
     jau
    1.38
    Activations Density 0.054%

    No Known Activations