© 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
    2. Gemma-3-4B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-16K
    4. 489
    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_12_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
     koncept
    0.23
     directly
    0.21
    莺
    0.21
     přímo
    0.21
    理解
    0.20
     Konzept
    0.20
     理解
    0.20
     informado
    0.20
     Movers
    0.20
     Directly
    0.19
    POSITIVE LOGITS
    くれます
    0.23
    ัม
    0.23
    Adds
    0.23
    lvm
    0.22
    Nome
    0.22
    vecb
    0.22
    Appending
    0.21
    
    0.21
    вии
    0.21
    Continue
    0.21
    Activations Density 0.000%

    No Known Activations