© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9355
    Prev
    Next
    INDEX
    Explanations

    code snippets within configuration files or programming languages

    oai_token-act-pair · gemini-2.0-flash

    relates to code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    P
    -0.43
     P
    -0.40
    ka
    -0.38
    while
    -0.38
     mo
    -0.38
      
    -0.37
    N
    -0.36
    sim
    -0.36
    __).
    -0.36
    ura
    -0.36
    POSITIVE LOGITS
    зулта
    0.91
     للمعارف
    0.88
    ьаж
    0.85
     itſelf
    0.80
    存于互联网档案馆
    0.77
    parsedMessage
    0.75
     صوتيه
    0.74
    RegressionTest
    0.73
    ConverterFactory
    0.72
    principalColumn
    0.72
    Activations Density 0.586%

    No Known Activations