Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7415
    Prev
    Next
    INDEX
    Explanations

    Chinese characters, names, Maven, file paths, and error messages

    oai_token-act-pair · gemini-2.0-flash

    Chinese characters

    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
     '
    -0.60
    手
    -0.57
     ‘
    -0.57
    nees
    -0.55
    も
    -0.55
    首
    -0.55
    WebElementEntity
    -0.52
    四
    -0.52
    -0.52
    神
    -0.52
    POSITIVE LOGITS
    <bos>
    1.15
     ouverts
    0.78
    ]")]
    0.78
     vectorielles
    0.77
     avoient
    0.76
     chré
    0.75
     للاسماء
    0.73
    __":
    0.73
     feroit
    0.73
    ]$}
    0.72
    Activations Density 1.126%

    No Known Activations