© 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. 10371
    Prev
    Next
    INDEX
    Explanations

    words related to race and gender, as well as the Clayman institute at Stanford

    oai_token-act-pair · gemini-2.0-flash

    black women

    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
     InputDecoration
    -0.79
    SequentialGroup
    -0.73
    AnchorStyles
    -0.69
    ViewFeatures
    -0.66
    FetchType
    -0.64
    iotensin
    -0.58
    istat
    -0.57
     оригіналу
    -0.57
    änglich
    -0.55
    Predecesor
    -0.54
    POSITIVE LOGITS
     invokingState
    0.68
    esModule
    0.64
     female
    0.55
     contemporaine
    0.54
    softc
    0.54
     kvin
    0.52
     africaine
    0.52
     norsk
    0.52
     svenska
    0.50
     femininos
    0.50
    Activations Density 1.133%

    No Known Activations