© 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. 11065
    Prev
    Next
    INDEX
    Explanations

    the word "Black", often in the context of ethnicity

    oai_token-act-pair · gemini-2.0-flash

    Black

    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
     Gleaner
    -0.55
    Pautan
    -0.55
     अं
    -0.54
    LEncoder
    -0.53
    archiviato
    -0.53
    ########.
    -0.52
     oprot
    -0.52
    Примітки
    -0.51
     soldati
    -0.49
     péné
    -0.49
    POSITIVE LOGITS
    ništvo
    0.62
    AndPassword
    0.55
    utnik
    0.54
    STERY
    0.53
    +#+#
    0.52
    addContainerGap
    0.51
     خارجية
    0.50
    latego
    0.49
    meer
    0.46
    ائص
    0.46
    Activations Density 0.666%

    No Known Activations