© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11565
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the features of buildings and homes, especially those emphasizing natural light and heating/cooling

    oai_token-act-pair · gemini-2.0-flash

    light coming through windows

    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
    <bos>
    -0.79
     '\\;'
    -0.77
    tagHelperRunner
    -0.75
     cherchés
    -0.74
    SharedCtor
    -0.73
     дописавши
    -0.69
     Roskov
    -0.69
    ाहरण
    -0.67
     StatelessWidget
    -0.65
    DebuggerNonUser
    -0.63
    POSITIVE LOGITS
    tų
    0.50
    makeConstraints
    0.48
    WindowConstants
    0.45
     outdoor
    0.43
     maux
    0.42
     balcón
    0.41
    ња
    0.41
     sound
    0.40
     interiores
    0.40
    ApiController
    0.40
    Activations Density 0.316%

    No Known Activations