© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10334
    Prev
    Next
    INDEX
    Explanations

    a mix of mathematical concepts such as operators or classes and social concepts like lifestyle and identifier

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    Personensuche
    -1.00
    GEBURTSDATUM
    -0.92
     виправивши
    -0.89
    expandindo
    -0.79
    انيف
    -0.78
     beginnetje
    -0.77
    MigrationBuilder
    -0.74
    yntaxException
    -0.71
    AndEndTag
    -0.69
    RTLD
    -0.68
    POSITIVE LOGITS
    fair
    0.55
     Fair
    0.54
    strato
    0.48
    Fair
    0.48
    ained
    0.47
    mgang
    0.47
    mitte
    0.46
    ease
    0.46
     fair
    0.46
    pread
    0.45
    Activations Density 1.511%

    No Known Activations