© 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. 3277
    Prev
    Next
    INDEX
    Explanations

    words with legal or legal-adjacent meaning in a document, potentially in the context of a legal case

    oai_token-act-pair · gemini-2.0-flash

    non-English

    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
    jspx
    -0.53
     coaxial
    -0.52
    TagHelper
    -0.50
    नु
    -0.49
    WindowListener
    -0.43
    UVWXYZ
    -0.42
     piezoelectric
    -0.42
    LayoutParams
    -0.42
     domésticos
    -0.41
     Demp
    -0.41
    POSITIVE LOGITS
    ंदीखरीदारी
    0.99
    EndProject
    0.82
     الدولى
    0.74
     Chwiliwch
    0.70
     comuniques
    0.69
     مرئيه
    0.66
    }))
    0.65
    IntoConstraints
    0.64
     betweenstory
    0.64
    verwijspagina
    0.63
    Activations Density 0.171%

    No Known Activations