© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11146
    Prev
    Next
    INDEX
    Explanations

    words related to international affairs, treaties, and legal contexts

    oai_token-act-pair · gemini-2.0-flash

    concerned

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     concerned
    -1.13
    concerned
    -1.04
     Concerned
    -0.79
     concern
    -0.73
    concern
    -0.66
     CONCERN
    -0.65
    Concer
    -0.61
    ServiceModel
    -0.59
    InstrumentedTest
    -0.58
     certain
    -0.52
    POSITIVE LOGITS
    AddTagHelper
    0.95
    ########.
    0.80
    ंदीखरीदारी
    0.70
    tagHelperRunner
    0.65
     kaarangay
    0.58
    UrlResolution
    0.57
     protoimpl
    0.57
    ParallelGroup
    0.54
    ISupport
    0.54
    unately
    0.53
    Activations Density 1.384%

    No Known Activations