© 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. 373
    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
     citas
    1.93
    \{
    1.92
    \{(
    1.83
    \|\
    1.83
     pues
    1.77
     scourge
    1.77
     جمله
    1.76
    ]={
    1.76
     cope
    1.71
     fuzzy
    1.70
    POSITIVE LOGITS
    ned
    2.28
    на
    2.15
    nia
    1.98
     isometry
    1.95
    šanas
    1.95
    prettier
    1.87
    ات
    1.87
    куру
    1.85
    aisseur
    1.85
    가
    1.84
    Activations Density 0.008%

    No Known Activations