© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2927
    Prev
    Next
    INDEX
    Explanations

    snippets of Spanish text within a document that is otherwise in English, especially simple and common words or phrases

    oai_token-act-pair · gemini-2.0-flash

    Code and Spanish

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Serviço
    -0.56
     betweenstory
    -0.55
     EconPapers
    -0.54
    EndGlobalSection
    -0.52
    SpringBootTest
    -0.52
    nocache
    -0.50
    $_['
    -0.49
     Darauf
    -0.49
    
    -0.49
     ddelweddau
    -0.48
    POSITIVE LOGITS
     intptr
    0.57
    govina
    0.52
    AxisAlignment
    0.51
    glers
    0.51
    ghum
    0.48
     nahilalakip
    0.48
     tasche
    0.47
     inflater
    0.47
    setObjectName
    0.47
    lês
    0.47
    Activations Density 0.956%

    No Known Activations