© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9765
    Prev
    Next
    INDEX
    Explanations

    instances of legal and business jargon related to agreements and responsibilities of involved parties

    oai_token-act-pair · gemini-2.0-flash

    company and consent-related terms

    np_token-act-pair-logits · gpt-4o-mini

    user agreements / licenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     purpoſe
    -0.87
    IntoConstraints
    -0.85
     bezeichneter
    -0.83
     reaſon
    -0.82
     Monfieur
    -0.74
     pleaſure
    -0.73
     poffible
    -0.71
     ſaid
    -0.71
     ſmall
    -0.70
     pegat
    -0.70
    POSITIVE LOGITS
     he
    0.56
    twimg
    0.54
     la
    0.50
     dis
    0.48
     cap
    0.47
     invece
    0.45
     bing
    0.45
    <eos>
    0.44
     Re
    0.43
     s
    0.43
    Activations Density 1.090%

    No Known Activations