© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6398
    Prev
    Next
    INDEX
    Explanations

    words pertaining to courts, crime, and punishment

    oai_token-act-pair · gemini-2.0-flash

    legal terms related to offenses and sentencing

    np_token-act-pair-logits · gpt-4o-mini

    crimes and offenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    IntoConstraints
    -0.93
    IUrlHelper
    -0.85
    GOTREF
    -0.78
     getItemId
    -0.73
     disambiguazione
    -0.72
    providedIn
    -0.70
    sizeCache
    -0.69
    yntaxException
    -0.67
    Jegyzetek
    -0.66
     pinulongan
    -0.66
    POSITIVE LOGITS
     nhau
    0.45
     pen
    0.44
     extra
    0.39
    czegó
    0.39
     Worthington
    0.39
    ticularly
    0.38
    лайн
    0.38
     noen
    0.38
    onets
    0.37
     pens
    0.37
    Activations Density 2.263%

    No Known Activations