© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13916
    Prev
    Next
    INDEX
    Explanations

    a variety of words that have some weak negative or emphatic association.

    oai_token-act-pair · gemini-2.0-flash

    repeated words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     GeoNames
    -0.69
    //});
    -0.66
    IntoConstraints
    -0.64
     utafitiHapana
    -0.63
    kháu
    -0.63
    /*---
    -0.62
    SequentialGroup
    -0.61
    Hochspringen
    -0.60
     gari
    -0.60
     Roskov
    -0.60
    POSITIVE LOGITS
    RenderAtEndOf
    0.64
     appelés
    0.57
     maux
    0.56
     aidé
    0.54
     aikana
    0.52
     avulla
    0.51
     tramonto
    0.50
     spéciaux
    0.50
     pioggia
    0.50
     cadrul
    0.49
    Activations Density 8.482%

    No Known Activations