© 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. 2518
    Prev
    Next
    INDEX
    Explanations

    code and documentation about bash scripts, and French words such as "pour," "chaque," "dossiers," "trouvé," etc

    oai_token-act-pair · gemini-2.0-flash

    Programming code and French text

    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
    Демографія
    -0.60
    stateProvider
    -0.56
     kasarigan
    -0.53
     udaler
    -0.52
     Faso
    -0.52
     snippetHide
    -0.51
    styleType
    -0.50
    Personendaten
    -0.50
    writeField
    -0.49
    stination
    -0.49
    POSITIVE LOGITS
    richtet
    0.58
     Wikimedijinoj
    0.52
     recuper
    0.51
     pre
    0.49
     prelimin
    0.48
     recovery
    0.48
    Recuper
    0.47
    FormatException
    0.47
    etes
    0.47
    曖昧さ回避
    0.47
    Activations Density 11.295%

    No Known Activations