© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8621
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to real estate sales and rental properties

    oai_token-act-pair · gemini-2.0-flash

    home

    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
     houses
    -1.15
     Houses
    -1.05
    Houses
    -1.00
    houses
    -0.90
    LabelTagHelper
    -0.75
     maisons
    -0.75
     Häuser
    -0.73
     dwellings
    -0.67
    House
    -0.66
     casas
    -0.63
    POSITIVE LOGITS
     home
    2.22
    home
    1.81
    Home
    1.54
     Home
    1.48
     HOME
    1.41
    HOME
    1.31
     hjem
    1.02
    ホーム
    0.91
     thuis
    0.82
    홈
    0.78
    Activations Density 4.917%

    No Known Activations