© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14237
    Prev
    Next
    INDEX
    Explanations

    text about politics and economics in cities and countries

    oai_token-act-pair · gemini-2.0-flash

    terms related to geopolitical contexts

    np_token-act-pair-logits · gpt-4o-mini

    Places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    titleMargin
    -0.64
     initComponents
    -0.59
     AppModule
    -0.59
    PerformLayout
    -0.57
    UserScript
    -0.55
    onViewCreated
    -0.53
     onAnimation
    -0.52
    RTEE
    -0.52
    kloped
    -0.51
    ItemBackground
    -0.50
    POSITIVE LOGITS
    ciatore
    0.63
     незавершена
    0.56
     الرياضيه
    0.55
     ModelExpression
    0.55
    ESSOR
    0.54
     akong
    0.51
    ::_('
    0.50
    GEBURTSDATUM
    0.50
    IContainer
    0.50
     hub
    0.50
    Activations Density 0.914%

    No Known Activations