© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6319
    Prev
    Next
    INDEX
    Explanations

    language frequently appearing in court reports

    oai_token-act-pair · gemini-2.0-flash

    legal profession

    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
     חיצוניים
    -0.79
     مواليد
    -0.77
     للاسماء
    -0.74
    StructEnd
    -0.73
     pinulongan
    -0.70
     poffe
    -0.69
     pleaſure
    -0.69
     myſelf
    -0.68
     raiſ
    -0.68
    ſelf
    -0.67
    POSITIVE LOGITS
    !*\
    0.68
     QC
    0.51
    ленко
    0.46
    saraba
    0.46
    kit
    0.45
     learned
    0.43
    Kit
    0.43
    ситет
    0.42
     aprendido
    0.42
     Man
    0.41
    Activations Density 1.157%

    No Known Activations