© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4679
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to everyday life and social situations

    oai_token-act-pair · gemini-2.0-flash

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     kontak
    -0.52
    ))));
    -0.50
    contact
    -0.50
    ]=>
    -0.49
     bords
    -0.49
     contact
    -0.49
    ())));
    -0.47
    atnya
    -0.47
    readystatechange
    -0.46
     Contact
    -0.45
    POSITIVE LOGITS
    IndentedString
    0.93
    RegressionTest
    0.70
     Pingback
    0.61
     contextLoads
    0.59
    psack
    0.59
    WebVitals
    0.58
    MemoryWarning
    0.57
    省市镇
    0.57
    VIAF
    0.55
    hdashline
    0.55
    Activations Density 1.394%

    No Known Activations