© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1319
    Prev
    Next
    INDEX
    Explanations

    place and person names, and related geographic terms, especially those relating to the middle east and northern Europe

    oai_token-act-pair · gemini-2.0-flash

    Geography

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     https
    -0.61
     Harris
    -0.53
    "}";
    -0.51
    )))
    -0.51
      
    -0.50
     
    -0.49
    ']){
    -0.49
    ''')
    -0.49
     Christiansen
    -0.49
    찮
    -0.48
    POSITIVE LOGITS
     geox
    0.69
     Mayweather
    0.68
    UserScript
    0.68
    SBATCH
    0.68
    PMailer
    0.66
     withal
    0.66
    rzej
    0.65
     AttributeSet
    0.65
     MyBatis
    0.65
    ();)
    0.64
    Activations Density 1.835%

    No Known Activations