© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15148
    Prev
    Next
    INDEX
    Explanations

    titles or descriptions of professions, especially in sports and military

    oai_token-act-pair · gemini-2.0-flash

    professional

    np_max-act-logits · gemini-2.0-flash

    say "professions"

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     InputDecoration
    -0.69
     StatelessWidget
    -0.69
     wrestler
    -0.68
     Wrestling
    -0.67
     wrestling
    -0.66
    Wrestling
    -0.65
    restling
    -0.64
     wrestlers
    -0.63
    RefNanny
    -0.61
     wrestle
    -0.59
    POSITIVE LOGITS
     professional
    0.95
     Professional
    0.92
    Professional
    0.90
     PROFESSIONAL
    0.89
    professional
    0.88
     professione
    0.71
     professionnelle
    0.71
    PROFESSIONAL
    0.69
     profesional
    0.64
     profes
    0.63
    Activations Density 2.484%

    No Known Activations