© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12257
    Prev
    Next
    INDEX
    Explanations

    what looks like the beginning of a year (19xx) followed by capitalized words or words related to legal or medical research

    oai_token-act-pair · gemini-2.0-flash

    numbered steps in documents

    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
    oa̍t
    -0.53
    GeneratedCode
    -0.51
     précédente
    -0.50
    )];
    -0.50
    )?;
    -0.50
    **
    -0.46
     """
    -0.46
    ArrayAdapter
    -0.45
    #+#
    -0.45
     sebelumnya
    -0.45
    POSITIVE LOGITS
    fromCharCode
    0.54
    setVerticalGroup
    0.53
     getopt
    0.52
    IsContent
    0.52
    MessageTagHelper
    0.49
     resourceCulture
    0.49
     صوتيه
    0.48
     common
    0.48
    contentLoaded
    0.48
    invokeLater
    0.47
    Activations Density 8.952%

    No Known Activations