© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15628
    Prev
    Next
    INDEX
    Explanations

    language related to a reunion of two people

    oai_token-act-pair · gemini-2.0-flash

    Uncommon, technical terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     saites
    -0.63
    atguigu
    -0.56
     transfieras
    -0.56
    AnimationsModule
    -0.55
    UrlResolution
    -0.55
    matchCondition
    -0.54
    thood
    -0.54
    uisine
    -0.52
    //};
    -0.52
     calendriers
    -0.52
    POSITIVE LOGITS
     للمعارف
    0.50
     surla
    0.47
    ParallelGroup
    0.47
    ië
    0.46
    XmlElement
    0.45
     camps
    0.45
    ApiException
    0.45
     Ajay
    0.44
    Erreferentziak
    0.44
     Lobo
    0.44
    Activations Density 2.696%

    No Known Activations