© 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. 3080
    Prev
    Next
    INDEX
    Explanations

    words pertaining to zoning and legal procedures related to property.

    oai_token-act-pair · gemini-2.0-flash

    real estate/property

    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
     '\\;'
    -0.67
    出版年
    -0.60
    IBOutlet
    -0.58
     betweenstory
    -0.57
     doGet
    -0.55
    וויק
    -0.52
    fromCharCode
    -0.50
     MessageBoxIcon
    -0.49
    AddTagHelper
    -0.49
    bootstrapcdn
    -0.49
    POSITIVE LOGITS
     Walkover
    0.54
     للاسماء
    0.52
    urten
    0.50
    site
    0.50
     Sites
    0.49
     ferma
    0.49
    usiai
    0.48
    racite
    0.48
    ]}"
    0.47
     pien
    0.46
    Activations Density 10.535%

    No Known Activations