© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8966
    Prev
    Next
    INDEX
    Explanations

    Vietnamese place names, especially those in the Mekong Delta region

    oai_token-act-pair · gemini-2.0-flash

    Vietnamese locations/language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     snippetHide
    -1.29
    MemoryWarning
    -1.28
     незавершена
    -1.26
    WriteBarrier
    -1.25
    enumi
    -1.25
    +:+
    -1.23
     متعلقه
    -1.22
     bezeichneter
    -1.20
     CreateTagHelper
    -1.20
    parsedMessage
    -1.18
    POSITIVE LOGITS
    ys
    0.26
    ,
    0.26
     in
    0.25
     for
    0.24
     
    0.23
    <eos>
    0.22
     its
    0.21
     to
    0.21
     that
    0.21
    かを
    0.21
    Activations Density 0.227%

    No Known Activations