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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12782
    Prev
    Next
    INDEX
    Explanations

    references to maritime legal cases, including ship names, legal terms, and citations

    oai_token-act-pair · gemini-2.0-flash

    technical terminologies and vessel names

    np_token-act-pair-logits · gpt-4o-mini

    ship

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     مُعرِّف
    -0.43
    HostException
    -0.41
    Deriv
    -0.40
    CrossRef
    -0.40
    AsStream
    -0.40
     griega
    -0.40
    ınır
    -0.39
     aspira
    -0.39
     griego
    -0.38
    ContentAsync
    -0.38
    POSITIVE LOGITS
     Waray
    0.73
    MemoryWarning
    0.69
    ImageContext
    0.68
    '){
    0.65
    новништво
    0.64
     ModelExpression
    0.64
     pinulongan
    0.63
    '},
    0.62
    "){
    0.60
    antMatchers
    0.60
    Activations Density 0.433%

    No Known Activations