© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4741
    Prev
    Next
    INDEX
    Explanations

    language related to roofs and architecture

    oai_token-act-pair · gemini-2.0-flash

    building materials and math

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     roof
    -1.74
     Roof
    -1.58
     roofs
    -1.55
     ROOF
    -1.53
    Roof
    -1.53
    roof
    -1.45
     rooftop
    -1.38
     rooftops
    -1.37
    Hat
    -1.27
     hats
    -1.26
    POSITIVE LOGITS
    TagMode
    0.50
    WaitGroup
    0.45
    曖昧さ回避
    0.44
    ArrowToggle
    0.44
     sl
    0.43
     Pork
    0.43
    myk
    0.42
     luk
    0.42
    міністра
    0.42
    issauga
    0.41
    Activations Density 1.687%

    No Known Activations