© 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. 6696
    Prev
    Next
    INDEX
    Explanations

    legal language and abbreviations, especially related to courts and legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    technical legal terms and entries

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

    Ohio legal documents

    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
    principalColumn
    -0.72
     kasarigan
    -0.71
    WaitGroup
    -0.69
    ✨:
    -0.69
    enderror
    -0.68
     requestCode
    -0.67
     ILogger
    -0.65
     الحره
    -0.65
    LabelTagHelper
    -0.64
    ::~
    -0.62
    POSITIVE LOGITS
    onViewCreated
    0.58
    \{\\
    0.50
    marshaller
    0.50
     oh
    0.45
    Value
    0.44
     WORTH
    0.44
     sikre
    0.43
     двой
    0.43
     OH
    0.41
    Achtung
    0.41
    Activations Density 0.874%

    No Known Activations