© 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. 358
    Prev
    Next
    INDEX
    Explanations

    tokens in a document that includes both numerical and french or similar language text

    oai_token-act-pair · gemini-2.0-flash

    Chat/Forum snippets

    np_max-act-logits · gemini-2.0-flash

    French function words

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     CreateTagHelper
    -0.81
    rungsseite
    -0.69
    swire
    -0.60
    WithIOException
    -0.60
     EdgeInsets
    -0.60
     متعلقه
    -0.60
    :][
    -0.57
    WebVitals
    -0.56
     /\.(
    -0.55
    InitVars
    -0.54
    POSITIVE LOGITS
     poud
    0.54
    udah
    0.50
     cérami
    0.49
    osene
    0.49
    LineNumber
    0.47
    θα
    0.47
     nôtre
    0.47
     pétrole
    0.47
    มาย
    0.46
    ců
    0.46
    Activations Density 1.121%

    No Known Activations