© 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. 9662
    Prev
    Next
    INDEX
    Explanations

    words, characters, and phrases used in specific, informal Internet chats, possibly related to a specific language or jargon.

    oai_token-act-pair · gemini-2.0-flash

    French 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
    WebVitals
    -0.63
    ViewFeatures
    -0.55
    __'
    -0.54
     cœurs
    -0.52
    NameInMap
    -0.52
    :✨
    -0.52
     &___
    -0.51
    parsedMessage
    -0.51
    `).
    -0.51
    MemoryWarning
    -0.50
    POSITIVE LOGITS
     betro
    0.42
     MUNDO
    0.42
     TRABAJO
    0.41
    abytes
    0.37
     ángel
    0.37
     ecosistema
    0.37
    uther
    0.37
     ESTADO
    0.36
     SOBRE
    0.36
     over
    0.35
    Activations Density 0.796%

    No Known Activations