© 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. 521
    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
    ians
    0.98
    LY
    0.88
     én
    0.84
    ക്കൊ
    0.80
    いますが
    0.78
    Myst
    0.78
    넛
    0.75
    把
    0.75
    ട്ട്
    0.74
    また
    0.74
    POSITIVE LOGITS
    ר
    0.85
     bagus
    0.81
     kena
    0.75
     retard
    0.74
     bakar
    0.74
    terus
    0.74
    ılan
    0.74
    ısı
    0.73
     económica
    0.72
     sore
    0.71
    Activations Density 0.022%

    No Known Activations