© 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. 2696
    Prev
    Next
    INDEX
    Explanations

    words related to legal, finance, and physics.

    oai_token-act-pair · gemini-2.0-flash

    legal entities, licensing, publications

    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
     الحره
    -1.08
    <bos>
    -0.66
     الرياضيه
    -0.62
     يتيمه
    -0.60
    vač
    -0.59
     للاسماء
    -0.58
    ├──
    -0.56
    AndEndTag
    -0.56
    ）』
    -0.55
    omiast
    -0.54
    POSITIVE LOGITS
    WithMany
    0.54
    ollectionView
    0.53
    devServer
    0.48
    uintptr
    0.47
    ValueGeneration
    0.47
     jogja
    0.47
    bcryptjs
    0.46
     Lumpur
    0.46
     MediatR
    0.46
     Sodom
    0.45
    Activations Density 5.613%

    No Known Activations