© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14316
    Prev
    Next
    INDEX
    Explanations

    German words

    oai_token-act-pair · gemini-2.0-flash

    german

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     يتيمه
    -0.47
    SharedCtor
    -0.46
    InputBorder
    -0.46
    pyplot
    -0.39
    borderTop
    -0.39
    bcryptjs
    -0.38
     S
    -0.37
     sociais
    -0.37
      
    -0.35
     Green
    -0.34
    POSITIVE LOGITS
     protoimpl
    0.78
    FormTagHelper
    0.77
     resourceCulture
    0.74
    numerusform
    0.72
    expandindo
    0.69
    troppo
    0.67
    TagMode
    0.66
     विश्वसनीयता
    0.66
    DispatchToProps
    0.66
     kaarangay
    0.66
    Activations Density 0.224%

    No Known Activations