© 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. 340
    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
    د
    0.79
    ве
    0.74
    да
    0.72
    ০
    0.68
    ل
    0.65
    ста
    0.63
    ли
    0.60
    т
    0.60
    জ
    0.60
    Я
    0.58
    POSITIVE LOGITS
    𝐢
    0.67
    𝐬
    0.65
     temperate
    0.62
    𝐩
    0.62
     fermions
    0.62
    ്യ
    0.60
     fadeIn
    0.59
     niego
    0.59
     surged
    0.58
     dwarfs
    0.58
    Activations Density 0.910%

    No Known Activations