© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1240
    Prev
    Next
    INDEX
    Explanations

    terms common in legal documents.

    oai_token-act-pair · gemini-2.0-flash

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     isn
    -2.08
     didn
    -2.03
     wasn
    -2.00
     doesn
    -1.98
     wouldn
    -1.97
     aren
    -1.96
     weren
    -1.94
    didn
    -1.91
    doesn
    -1.90
    wouldn
    -1.83
    POSITIVE LOGITS
     do
    1.03
    do
    0.82
     Do
    0.80
    Do
    0.80
     does
    0.56
    edenken
    0.55
     doing
    0.54
     متعلقه
    0.53
    ImageField
    0.53
    prisma
    0.52
    Activations Density 4.734%

    No Known Activations