© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11211
    Prev
    Next
    INDEX
    Explanations

    language related to consumer advocacy and environmentalism

    oai_token-act-pair · gemini-2.0-flash

    Groups and organizations

    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
     AssemblyProduct
    -0.81
    WriteBarrier
    -0.77
    GRAFIA
    -0.71
    abestanden
    -0.69
    invokeLater
    -0.66
    glMatrixMode
    -0.66
    ecuzione
    -0.65
    NOPQRST
    -0.63
    исленность
    -0.63
    msgSender
    -0.60
    POSITIVE LOGITS
    <bos>
    0.91
    Välislingid
    0.52
    სქოლიო
    0.51
     opposition
    0.47
    Opposition
    0.45
     dénon
    0.44
     campaigned
    0.43
    UserScript
    0.40
     filed
    0.40
    Don
    0.39
    Activations Density 1.643%

    No Known Activations