© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3601
    Prev
    Next
    INDEX
    Explanations

    language related to international collaboration on terrorism and security, particularly emphasizing the strengthening of efforts and information sharing.

    oai_token-act-pair · gemini-2.0-flash

    terms related to counterterrorism and security

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

    cooperation

    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
    GMENT
    -0.58
     élas
    -0.49
    ņas
    -0.48
     själ
    -0.48
     Riding
    -0.47
    wakili
    -0.47
    ราะ
    -0.47
     composición
    -0.46
     bénéfic
    -0.46
     primal
    -0.46
    POSITIVE LOGITS
    WindowConstants
    0.71
     bilateral
    0.64
    InjectAttribute
    0.63
    DidLoad
    0.61
     ویکی‌پدی
    0.60
    queryInterface
    0.58
     cooperation
    0.58
    DebuggerStep
    0.57
     esternos
    0.56
     sko
    0.56
    Activations Density 1.313%

    No Known Activations