© 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. 2980
    Prev
    Next
    INDEX
    Explanations

    the word "White," often in the context of politics or race

    oai_token-act-pair · gemini-2.0-flash

    instances of "White"

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

    White

    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
    IonicModule
    -0.61
     समीक्षाओं
    -0.59
     صوتيه
    -0.57
     NKC
    -0.57
    IVEREF
    -0.54
     disambiguazione
    -0.53
     الرياضيه
    -0.53
    MessageTagHelper
    -0.53
    ✨:
    -0.52
    ()");
    -0.51
    POSITIVE LOGITS
    참고
    0.72
    ">//
    0.55
    WebApplication
    0.49
    CHAP
    0.49
    rootDir
    0.47
    basicConfig
    0.47
    hä
    0.47
    cente
    0.47
     Edg
    0.46
    haca
    0.46
    Activations Density 0.431%

    No Known Activations