© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10172
    Prev
    Next
    INDEX
    Explanations

    words and names related to legal documents, places, people, and governments

    oai_token-act-pair · gemini-2.0-flash

    legal context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <b>
    -0.72
    <u>
    -0.71
    <i>
    -0.66
    <strong>
    -0.66
    esai
    -0.66
    </i>
    -0.64
    Демографія
    -0.60
     a
    -0.59
    </b>
    -0.58
     really
    -0.58
    POSITIVE LOGITS
     Efq
    1.04
     Jefus
    1.01
     Eſ
    0.98
     Houſe
    0.96
    ſelf
    0.95
     Majefty
    0.93
     Monfieur
    0.91
     Conſ
    0.91
     purpoſe
    0.90
     Diſ
    0.90
    Activations Density 6.171%

    No Known Activations