© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7026
    Prev
    Next
    INDEX
    Explanations

    legal and political terms and phrases

    oai_token-act-pair · gemini-2.0-flash

    say "law"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     law
    -2.02
    Law
    -1.93
     Law
    -1.91
     legal
    -1.88
     LAW
    -1.86
    law
    -1.85
    legal
    -1.76
    Legal
    -1.76
     Laws
    -1.76
     laws
    -1.75
    POSITIVE LOGITS
    aw
    0.38
     سانت
    0.38
     low
    0.36
    例文帳に追加
    0.35
    شهاد
    0.35
     Personal
    0.35
    <bos>
    0.33
    rina
    0.33
     zal
    0.32
    ah
    0.31
    Activations Density 1.879%

    No Known Activations