© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13412
    Prev
    Next
    INDEX
    Explanations

    words related to raising children and childhood

    oai_token-act-pair · gemini-2.0-flash

    raise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    dorfer
    -0.56
    tiker
    -0.50
    lucene
    -0.50
    号
    -0.50
    routeProvider
    -0.50
    amzn
    -0.49
    artik
    -0.49
    Memento
    -0.49
    φό
    -0.49
    ricle
    -0.49
    POSITIVE LOGITS
     pinulongan
    0.91
     transfieras
    0.88
    MLLoader
    0.88
    expandindo
    0.82
    PyExc
    0.75
    Portály
    0.72
     समीक्षाओं
    0.72
     referenties
    0.71
    RegistryLite
    0.68
    styleType
    0.68
    Activations Density 2.174%

    No Known Activations