© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8595
    Prev
    Next
    INDEX
    Explanations

    mentions of text in other languages, particularly French or Italian

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    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
     propOrder
    -0.99
    IContainer
    -0.83
     AssemblyCulture
    -0.78
     resourceCulture
    -0.74
    AccessorTable
    -0.71
     CreateTagHelper
    -0.71
    awtextra
    -0.67
    HomeAsUpEnabled
    -0.67
    webElementXpaths
    -0.65
    NameInMap
    -0.65
    POSITIVE LOGITS
    фициальный
    0.44
    Distribución
    0.43
     đóng
    0.43
    liğ
    0.42
     folle
    0.42
    Спо
    0.41
    inger
    0.41
    pi
    0.41
    stal
    0.41
     jeter
    0.40
    Activations Density 0.353%

    No Known Activations