© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14680
    Prev
    Next
    INDEX
    Explanations

    references to government, inventions, and race

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ########.
    -0.77
    URLException
    -0.70
    
    -0.67
     betweenstory
    -0.63
    }>;
    -0.63
     مشين
    -0.60
    featureID
    -0.60
    )');
    -0.58
    >>;
    -0.58
    \"");
    -0.57
    POSITIVE LOGITS
    RectangleBorder
    0.59
    <bos>
    0.57
    ToMany
    0.55
     set
    0.53
    twimg
    0.52
    requireNonNull
    0.52
     head
    0.50
     fasi
    0.49
     phase
    0.49
    ு
    0.48
    Activations Density 5.804%

    No Known Activations