© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5213
    Prev
    Next
    INDEX
    Explanations

    the definite article "the", sometimes around superlatives

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'rest'

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

    rest

    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
     propOrder
    -0.82
     désolés
    -0.82
     ujednoznacz
    -0.81
    ChildScrollView
    -0.79
     vectorielles
    -0.79
    Datuak
    -0.79
    AnimationsModule
    -0.79
     ModelRenderer
    -0.78
    webElementXpaths
    -0.77
     MessageBoxIcon
    -0.77
    POSITIVE LOGITS
     rest
    0.77
    rest
    0.56
     reste
    0.50
    Rest
    0.48
     usual
    0.48
     list
    0.47
     Rest
    0.47
     üb
    0.47
    list
    0.46
     типи
    0.43
    Activations Density 1.622%

    No Known Activations