© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10042
    Prev
    Next
    INDEX
    Explanations

    mentions of ethnicity

    oai_token-act-pair · gemini-2.0-flash

    Middle East and India

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ########.
    -0.63
    ViewImports
    -0.61
    archiviato
    -0.60
    ArgsConstructor
    -0.59
     galería
    -0.54
     abzu
    -0.54
     Foy
    -0.53
    MetaObject
    -0.53
     primas
    -0.52
    VIER
    -0.52
    POSITIVE LOGITS
    aarrggbb
    0.59
     doInBackground
    0.55
    AnchorTagHelper
    0.52
     Indus
    0.50
     Indi
    0.48
     Quill
    0.47
    hoeddwyd
    0.46
     optique
    0.44
    Sub
    0.44
    >[]
    0.44
    Activations Density 1.251%

    No Known Activations