© 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. 4114
    Prev
    Next
    INDEX
    Explanations

    tokens that appear to be related to legal and political documents or language

    oai_token-act-pair · 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
     تضيفلها
    -0.79
    FormTagHelper
    -0.76
     للاسماء
    -0.75
     intptr
    -0.75
    +#+#
    -0.74
    NewUrlParser
    -0.72
    CppMethod
    -0.71
    ьаж
    -0.69
    Tembelea
    -0.69
    yntaxException
    -0.68
    POSITIVE LOGITS
    autoconfigure
    0.43
    GIVEREF
    0.40
    unistd
    0.39
    Kira
    0.39
    ""}
    0.37
     uska
    0.36
     grano
    0.36
    Население
    0.35
    liko
    0.35
    下的
    0.34
    Activations Density 2.613%

    No Known Activations