© 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. 5054
    Prev
    Next
    INDEX
    Explanations

    things related to opera and musical performance

    oai_token-act-pair · gemini-2.0-flash

    context related to operatic roles or characters

    np_token-act-pair-logits · gpt-4o-mini
    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
     kasarigan
    -0.72
    onomía
    -0.63
    TargetException
    -0.57
     referenties
    -0.54
     ProtoMessage
    -0.54
    ceedings
    -0.52
    참고
    -0.51
     الفلك
    -0.51
     linkovi
    -0.50
    WebControls
    -0.49
    POSITIVE LOGITS
    devamını
    0.49
    zei
    0.48
    
    0.47
     tax
    0.47
     jenner
    0.46
    GeneratedCode
    0.45
    delwed
    0.45
     tł
    0.44
    SHADOW
    0.44
     end
    0.43
    Activations Density 0.440%

    No Known Activations