© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1664
    Prev
    Next
    INDEX
    Explanations

    content related to immigration, specifically requiring background checks and police clearance certificates.

    oai_token-act-pair · gemini-2.0-flash

    legal clearances and background checks

    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
    UPAC
    -0.62
    Hozzáférés
    -0.57
    VideoCapture
    -0.55
    OrNil
    -0.55
    TypedDataSet
    -0.55
    Identyfik
    -0.54
     inflater
    -0.52
     Reverso
    -0.50
    abstractmethod
    -0.49
    owanym
    -0.49
    POSITIVE LOGITS
    TagMode
    0.59
     يتيمه
    0.54
     transfieras
    0.54
    الحياه
    0.53
    principalTable
    0.52
     filtros
    0.52
     diligence
    0.50
    "):
    0.49
    encodeWith
    0.48
    ThroughAttribute
    0.48
    Activations Density 1.438%

    No Known Activations