© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11592
    Prev
    Next
    INDEX
    Explanations

    names of people

    oai_token-act-pair · gemini-2.0-flash

    research papers and authors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    aarrggbb
    -0.78
    ();)
    -0.77
    ########.
    -0.77
    featureID
    -0.75
     الحره
    -0.75
     AssemblyProduct
    -0.74
     disambiguazione
    -0.72
     تضيفلها
    -0.68
     للمعارف
    -0.68
    AndEndTag
    -0.68
    POSITIVE LOGITS
    <eos>
    0.57
     colour
    0.56
    ,
    0.46
     Alexander
    0.45
    Colour
    0.45
    colour
    0.44
    edema
    0.43
     training
    0.43
    class
    0.41
     C
    0.41
    Activations Density 0.511%

    No Known Activations