© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4341
    Prev
    Next
    INDEX
    Explanations

    language related to legal disputes, contracts, and formal agreements

    oai_token-act-pair · gemini-2.0-flash

    arguments and claims

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    rawDesc
    -0.69
    principalColumn
    -0.68
    Kjelder
    -0.65
     okuyayım
    -0.62
    >--}}
    -0.59
     Audiodateien
    -0.58
    Atsauces
    -0.57
     typelib
    -0.56
     للمعارف
    -0.55
    yntaxException
    -0.55
    POSITIVE LOGITS
     оригіналу
    0.55
    pozycji
    0.45
    불
    0.43
     fique
    0.43
    ictwa
    0.42
    ndag
    0.42
    原始内容存档于
    0.41
    ittäin
    0.41
    imak
    0.40
     dolay
    0.40
    Activations Density 16.877%

    No Known Activations