© 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. 13932
    Prev
    Next
    INDEX
    Explanations

    words and phrases from news reports about political unrest and violence

    oai_token-act-pair · gemini-2.0-flash

    countries and adjectives

    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
    ViewImports
    -0.66
    mybatisplus
    -0.65
    ++]=
    -0.55
    HasForeignKey
    -0.54
    %%%%%%%%%%%%%%%%
    -0.54
    )++;
    -0.53
     المعيارى
    -0.51
     GENERATED
    -0.49
    \,,
    -0.48
    ::::::::::::::::
    -0.48
    POSITIVE LOGITS
     Chinese
    1.21
     China
    1.20
    Chinese
    1.10
    China
    1.08
     Russian
    1.06
     CHINESE
    1.06
     CHINA
    1.02
     Italian
    1.02
     German
    1.02
     Russia
    0.99
    Activations Density 2.648%

    No Known Activations