© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 335
    Prev
    Next
    INDEX
    Explanations

    noun phrases modifying people, especially concerning profession or demographic

    oai_token-act-pair · gemini-2.0-flash

    professions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Swedes
    -0.68
    BeginContext
    -0.63
     Greeks
    -0.62
     Russians
    -0.61
     whites
    -0.60
     Germans
    -0.59
     Spaniards
    -0.59
     Italians
    -0.57
     Soviets
    -0.56
     anaknya
    -0.55
    POSITIVE LOGITS
     adult
    0.79
    findpost
    0.71
     executive
    0.69
     professional
    0.68
     mortal
    0.68
    adult
    0.67
     ADULT
    0.65
     Republican
    0.62
    executive
    0.62
    Adult
    0.60
    Activations Density 3.687%

    No Known Activations