© 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. 4639
    Prev
    Next
    INDEX
    Explanations

    instances of something being displayed, demonstrated, or revealed.

    oai_token-act-pair · gemini-2.0-flash

    interrogative words or phrases

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

    showing something

    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
    setViewportView
    -0.59
    SequentialGroup
    -0.57
    posedge
    -0.56
    jsdelivr
    -0.51
    withstanding
    -0.50
     cherchés
    -0.50
    alyptus
    -0.50
    bootstrapcdn
    -0.49
    cal
    -0.48
     merce
    -0.47
    POSITIVE LOGITS
     how
    0.98
     why
    0.77
     bagaimana
    0.70
     CreateTagHelper
    0.64
     what
    0.63
     protoimpl
    0.63
     esternos
    0.63
    帖最后由
    0.63
     us
    0.61
     HOW
    0.60
    Activations Density 8.794%

    No Known Activations