© 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. 1090
    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
    𝒚
    3.26
    儡
    2.79
    𝒔
    2.63
    𝙩
    2.56
    𝙤
    2.53
    𝙮
    2.49
    𝙘
    2.43
    recyclerView
    2.42
    ⎯
    2.42
    startDate
    2.41
    POSITIVE LOGITS
    ا
    3.41
    ą
    3.05
    й
    2.72
    al
    2.60
     впечатление
    2.57
    ının
    2.55
    ar
    2.42
    Х
    2.39
    مثل
    2.39
    ди
    2.39
    Activations Density 0.018%

    No Known Activations