© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4092
    Prev
    Next
    INDEX
    Explanations

    citations and references to outside material, particularly with the word "refer."

    oai_token-act-pair · gemini-2.0-flash

    references to audience

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

    say "to readers"

    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
    تقاوى
    -0.43
    jspx
    -0.38
     caps
    -0.37
    enumii
    -0.37
     internally
    -0.37
    Immobili
    -0.37
     kain
    -0.35
    Customers
    -0.35
     booth
    -0.35
    CellStyle
    -0.34
    POSITIVE LOGITS
     audience
    1.16
     AUD
    0.94
     Audience
    0.93
    audience
    0.93
     audiences
    0.89
     audiencia
    0.89
     publiek
    0.87
    AUD
    0.86
    audi
    0.85
     audi
    0.84
    Activations Density 1.218%

    No Known Activations