© 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. 12274
    Prev
    Next
    INDEX
    Explanations

    text which describes playing sports along with possible related injuries

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "professional"

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

    Professional

    np_max-act-logits · gemini-2.0-flash

    say "sports"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     giustizia
    -0.65
    AxisAlignment
    -0.61
    جوايز
    -0.56
    MemoryWarning
    -0.53
    렷
    -0.53
     Nước
    -0.52
    quitous
    -0.52
    icorn
    -0.52
     chert
    -0.51
     protoimpl
    -0.50
    POSITIVE LOGITS
     professional
    1.09
    professional
    1.01
     Professional
    0.94
    Professional
    0.90
     profesional
    0.83
     PROFESSIONAL
    0.83
     amateur
    0.82
     contact
    0.79
     elite
    0.76
     professionalism
    0.74
    Activations Density 1.315%

    No Known Activations