© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11503
    Prev
    Next
    INDEX
    Explanations

    instances of something being clear, obvious, or evident

    oai_token-act-pair · gemini-2.0-flash

    clear

    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
    mybatisplus
    -0.59
    ίδι
    -0.50
     PyLong
    -0.48
    fjspx
    -0.47
     itinéraires
    -0.45
     affaires
    -0.45
     poda
    -0.44
     Imágenes
    -0.44
     BorderRadius
    -0.44
      
    -0.43
    POSITIVE LOGITS
     duidelijk
    0.70
    Clearly
    0.69
     Clearly
    0.67
    CLEAR
    0.67
     clear
    0.65
     clearly
    0.65
     CLEAR
    0.64
     تانيه
    0.63
     facie
    0.63
    clearly
    0.62
    Activations Density 0.905%

    No Known Activations