© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 15457
    Prev
    Next
    INDEX
    Explanations

    proper nouns and associated words within specific topics

    oai_token-act-pair · gemini-2.0-flash

    News articles or biographies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     câte
    -0.55
     väx
    -0.54
     eccell
    -0.51
     doméstico
    -0.50
     nakalista
    -0.50
     cantit
    -0.49
     înal
    -0.49
     voks
    -0.49
     himo
    -0.48
    ation
    -0.47
    POSITIVE LOGITS
    hoeddwyd
    0.69
    Portale
    0.66
    SBATCH
    0.65
    IContainer
    0.63
    참고
    0.60
    ISupport
    0.60
    AndView
    0.60
    حوالہ
    0.58
     وتسجيلات
    0.57
     getSystem
    0.57
    Activations Density 0.842%

    No Known Activations