© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7806
    Prev
    Next
    INDEX
    Explanations

    language used in legal contracts, especially related to warranties, damages, or legal code

    oai_token-act-pair · gemini-2.0-flash

    Legal contracts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    Personendaten
    -0.77
     tangents
    -0.59
    msgTypes
    -0.59
    setVerticalGroup
    -0.57
    ViewChild
    -0.54
    
    -0.54
    ximate
    -0.54
    getColumnIndex
    -0.53
     referenties
    -0.53
    DispatchToProps
    -0.52
    POSITIVE LOGITS
     JpaRepository
    0.56
    fromnode
    0.55
    InputTagHelper
    0.50
    ेत्र
    0.47
    таратура
    0.46
     cuales
    0.46
     niente
    0.45
    vismo
    0.45
    for
    0.44
    희
    0.44
    Activations Density 2.166%

    No Known Activations