© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4889
    Prev
    Next
    INDEX
    Explanations

    words that end in 'al' or 'ale' that are associated with a negative association with leaders, groups and violence

    oai_token-act-pair · gemini-2.0-flash

    ale

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ale
    -1.20
    ALE
    -1.02
     Gu
    -0.90
    gu
    -0.90
    Gu
    -0.82
    GU
    -0.77
     GU
    -0.76
     ale
    -0.73
     gu
    -0.72
    ole
    -0.71
    POSITIVE LOGITS
     مرئيه
    0.62
     AssemblyCulture
    0.60
    AddTagHelper
    0.59
    forRoot
    0.57
    AddHtmlAttribute
    0.57
    rceil
    0.54
     Olympedia
    0.54
    MigrationBuilder
    0.52
    esModule
    0.50
    reportWebVitals
    0.50
    Activations Density 9.232%

    No Known Activations