© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1896
    Prev
    Next
    INDEX
    Explanations

    language about governmental bodies, actions, and structures.

    oai_token-act-pair · gemini-2.0-flash

    Politics and power

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    AddTagHelper
    -1.02
    sizeCache
    -0.88
    tagHelperRunner
    -0.82
    WebServlet
    -0.81
    StoryboardSegue
    -0.79
     unknownFields
    -0.78
    HasForeignKey
    -0.77
     endwhile
    -0.77
    ГЛА
    -0.76
    featureID
    -0.75
    POSITIVE LOGITS
     Einsch
    0.49
     acceleration
    0.43
    fts
    0.42
    actual
    0.42
    kates
    0.41
    Acceleration
    0.41
     Actual
    0.40
    istical
    0.40
    Actual
    0.40
    tacle
    0.39
    Activations Density 4.191%

    No Known Activations