© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14658
    Prev
    Next
    INDEX
    Explanations

    language from judicial opinions and legal documents.

    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
     activos
    -0.47
     SwiftUI
    -0.43
    ..\..\
    -0.42
     GoogleFonts
    -0.41
    SetActive
    -0.41
    []):
    -0.41
    AttributeSet
    -0.40
    催
    -0.39
    ASSE
    -0.39
    Hee
    -0.39
    POSITIVE LOGITS
    хьтан
    0.81
    addCriterion
    0.81
     تضيفلها
    0.79
    IUrlHelper
    0.79
    oredCriteria
    0.75
     мәкал
    0.72
    CloseOperation
    0.70
    ArgsConstructor
    0.69
    Personensuche
    0.69
    WindowListener
    0.68
    Activations Density 4.648%

    No Known Activations