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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 744
    Prev
    Next
    INDEX
    Explanations

    elementary schools with numbers in their addresses

    oai_token-act-pair · gemini-2.0-flash

    Addresses and IDs

    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
     hausse
    -0.54
    NewUrlParser
    -0.52
    yonel
    -0.50
    LabelTagHelper
    -0.48
    การณ์
    -0.45
     whoſe
    -0.44
    Referanser
    -0.43
     quede
    -0.43
    ensão
    -0.43
    pleft
    -0.42
    POSITIVE LOGITS
    0
    0.74
     bezeichneter
    0.70
     Normdatei
    0.64
    
    0.63
    2
    0.59
     Picchu
    0.59
    تقاوى
    0.59
     AssemblyCompany
    0.58
     Enterprise
    0.57
    5
    0.57
    Activations Density 20.938%

    No Known Activations