© 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. 1089
    Prev
    Next
    INDEX
    Explanations

    proper nouns and other named entities.

    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
     lección
    -0.54
     daglig
    -0.48
     undervis
    -0.47
     hozz
    -0.46
     soledad
    -0.45
     rette
    -0.44
     unidos
    -0.44
     perdón
    -0.44
     utford
    -0.43
     ansvar
    -0.43
    POSITIVE LOGITS
     تضيفلها
    0.81
    Geplaatst
    0.78
     itſelf
    0.74
     ſy
    0.72
    ſelves
    0.71
    الحياه
    0.71
    )";
    0.71
    ſelf
    0.71
    InvalidProtocol
    0.70
     }}$}
    0.69
    Activations Density 14.571%

    No Known Activations