© 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. 684
    Prev
    Next
    INDEX
    Explanations

    words related to agreements, laws, authentication, or diseases.

    oai_token-act-pair · 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
     enfans
    -0.65
     verità
    -0.61
     hänen
    -0.60
     nyky
    -0.60
     Euse
    -0.59
     marbre
    -0.58
    pportun
    -0.58
     érde
    -0.57
    
    -0.56
     säll
    -0.56
    POSITIVE LOGITS
    URLException
    0.77
     Penh
    0.72
    RectangleBorder
    0.69
    orianCalendar
    0.69
    InteropServices
    0.65
    kian
    0.61
    medriver
    0.61
    incón
    0.60
    ruptedException
    0.60
    DoubleQuotes
    0.59
    Activations Density 10.466%

    No Known Activations