© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7149
    Prev
    Next
    INDEX
    Explanations

    strings of characters that look like scientific references and formulas, particularly in the context of scientific publications

    oai_token-act-pair · gemini-2.0-flash

    Code/technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    cjonal
    -0.42
    躁
    -0.38
    bondale
    -0.36
     Nein
    -0.35
    orologio
    -0.34
    appartamento
    -0.34
    Bigr
    -0.34
     Dem
    -0.34
     an
    -0.33
    udin
    -0.33
    POSITIVE LOGITS
    tagHelperRunner
    1.12
    +#+#
    0.93
     الرياضيه
    0.81
     AssemblyCulture
    0.79
    UnusedPrivate
    0.79
     himo
    0.78
    IUrlHelper
    0.78
    inghouse
    0.78
    hearts
    0.77
     homology
    0.77
    Activations Density 6.646%

    No Known Activations