© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15948
    Prev
    Next
    INDEX
    Explanations

    words related to legal concepts, arguments, and judgements

    oai_token-act-pair · gemini-2.0-flash

    Legal context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     users
    -1.78
     Users
    -1.73
     user
    -1.63
    Users
    -1.61
    users
    -1.51
    用户
    -1.48
     customers
    -1.46
    user
    -1.41
    Customers
    -1.37
     Customers
    -1.36
    POSITIVE LOGITS
    MigrationBuilder
    0.73
    IntoConstraints
    0.69
     Baillargeon
    0.63
     Spisak
    0.62
     AspNetCore
    0.59
    Personendaten
    0.58
    ]--;
    0.57
    ArgsConstructor
    0.55
     '\\;'
    0.55
    ]='\
    0.54
    Activations Density 5.193%

    No Known Activations