© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7498
    Prev
    Next
    INDEX
    Explanations

    the word "Asian" and related terms like "Pacific"

    oai_token-act-pair · gemini-2.0-flash

    Asian

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     Watch
    -0.75
    Beware
    -0.74
     watch
    -0.73
     Beware
    -0.73
     beware
    -0.72
    Watch
    -0.69
    watch
    -0.67
     alerta
    -0.66
    principalTable
    -0.64
    Caution
    -0.63
    POSITIVE LOGITS
     BoxFit
    0.66
    AccessorTable
    0.60
     himo
    0.59
     >=",
    0.59
     favorably
    0.58
    bootstrapcdn
    0.56
    Bibliograf
    0.56
    classmethod
    0.54
    cture
    0.52
    /-/
    0.52
    Activations Density 0.251%

    No Known Activations