© 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. 228
    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
    \<^
    2.22
    ures
    1.90
    مانی
    1.84
    \<
    1.83
    
    1.81
     '/'
    1.81
    brando
    1.81
    هم
    1.81
     sementara
    1.81
     IUE
    1.79
    POSITIVE LOGITS
    𝐫
    2.10
    ן
    2.09
    𝚕
    2.07
    ر
    2.02
    ની
    1.94
     reputations
    1.94
    𝐞
    1.94
    ла
    1.91
    Forgery
    1.90
    ৯
    1.89
    Activations Density 0.252%

    No Known Activations