© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 371
    Prev
    Next
    INDEX
    Explanations

    language related to law and legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    legal context

    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
    saraba
    -0.74
    AxisAlignment
    -0.68
    AnchorTagHelper
    -0.65
    SPATH
    -0.60
    脚注の使い方
    -0.60
    qrstuvwxyz
    -0.59
    Билгалдахарш
    -0.57
    Viited
    -0.57
    hlands
    -0.55
    InstanceState
    -0.54
    POSITIVE LOGITS
     تانيه
    0.62
     nifer
    0.58
     nawr
    0.53
     ProductService
    0.52
     Conversion
    0.52
     conversion
    0.49
     CiNii
    0.48
     Fulton
    0.48
     himſelf
    0.47
     Osna
    0.47
    Activations Density 4.745%

    No Known Activations