© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14042
    Prev
    Next
    INDEX
    Explanations

    seemingly random Sanskrit/Kannada words, possibly related to a specific religious text or tradition.

    oai_token-act-pair · gemini-2.0-flash

    Mixed languages and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     canadienne
    -0.80
     bénéfices
    -0.78
     étrangère
    -0.78
     henkil
    -0.76
     ouvriers
    -0.76
     hırka
    -0.75
     sanitaires
    -0.75
     mauvaises
    -0.74
     journaux
    -0.74
     judicia
    -0.74
    POSITIVE LOGITS
     MenuView
    0.47
    ItemBackground
    0.47
     ②
    0.46
     ③
    0.46
     AssemblyTitle
    0.45
    WriteTagHelper
    0.44
     AssemblyProduct
    0.43
    ſelf
    0.43
    ſelves
    0.43
     Efq
    0.41
    Activations Density 3.809%

    No Known Activations