© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12414
    Prev
    Next
    INDEX
    Explanations

    words related to law, lawsuits, and legal judgements.

    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
    بوابة
    -0.58
    complexContent
    -0.55
    stdc
    -0.55
    netbeans
    -0.53
    versch
    -0.50
    pubmed
    -0.50
    XmlNode
    -0.49
    Bibliograf
    -0.48
     Dim
    -0.47
    ioutil
    -0.47
    POSITIVE LOGITS
     متعلقه
    0.76
    новништво
    0.68
    niosek
    0.55
    initView
    0.52
     utafitiHapana
    0.52
    Зноскі
    0.50
    soever
    0.50
    ContentAsync
    0.49
     województwie
    0.48
     Falta
    0.48
    Activations Density 9.857%

    No Known Activations