© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14865
    Prev
    Next
    INDEX
    Explanations

    the city of Hong Kong combined with the word "University"

    oai_token-act-pair · gemini-2.0-flash

    Kong

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ↵↵
    -0.87
     
    -0.83
    "
    -0.79
    <bos>
    -0.77
    '
    -0.76
    ↵
    -0.75
    1
    -0.71
     "
    -0.69
    2
    -0.68
    <strong>
    -0.67
    POSITIVE LOGITS
    存于互联网档案馆
    1.34
    featureID
    1.34
     lenker
    1.33
    ########.
    1.27
    клопе
    1.24
    bootstrapcdn
    1.23
     disambiguazione
    1.21
     NSCoder
    1.20
    出版年
    1.20
    #+#
    1.17
    Activations Density 0.435%

    No Known Activations