© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13912
    Prev
    Next
    INDEX
    Explanations

    technical terms related to professions, education and economics

    oai_token-act-pair · gemini-2.0-flash

    variations of "pro"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     professional
    -1.17
     expert
    -1.16
    professional
    -1.13
    Professional
    -1.13
     Professional
    -1.05
     Expert
    -1.02
    expert
    -0.98
     PROFESSIONAL
    -0.94
     specialist
    -0.93
    Expert
    -0.92
    POSITIVE LOGITS
     pros
    0.91
     Pros
    0.81
    Pros
    0.78
    pros
    0.76
    PROS
    0.66
    CONSIN
    0.54
     henvisninger
    0.54
    Personendaten
    0.51
     tors
    0.51
     heads
    0.50
    Activations Density 2.343%

    No Known Activations