© 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. 10059
    Prev
    Next
    INDEX
    Explanations

    words related to real estate purchasing and home ownership

    oai_token-act-pair · gemini-2.0-flash

    housing

    np_max-act · 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
    ssic
    -0.52
    zusch
    -0.47
     late
    -0.46
     from
    -0.46
    kjø
    -0.44
    readValue
    -0.43
    onis
    -0.43
     fidélité
    -0.43
    vic
    -0.43
    ass
    -0.43
    POSITIVE LOGITS
    webElementXpaths
    0.87
    Попис
    0.77
    BeginContext
    0.77
    fromnode
    0.68
    TintMode
    0.66
    WithIOException
    0.66
    WriteBarrier
    0.66
    utilisons
    0.66
     cherchés
    0.64
     становника
    0.63
    Activations Density 0.328%

    No Known Activations