© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8923
    Prev
    Next
    INDEX
    Explanations

    numerical information relating to buildings and places located in a specific area, including addresses and building dimensions

    oai_token-act-pair · gemini-2.0-flash

    Building levels/floors

    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
    FormTagHelper
    -0.72
    kháu
    -0.62
     vectorielle
    -0.59
    ItemBackground
    -0.56
     giapp
    -0.56
     jspb
    -0.54
     prisms
    -0.53
    resave
    -0.52
     grupper
    -0.52
     Aérea
    -0.52
    POSITIVE LOGITS
     continúas
    0.51
    }}}}
    0.51
    )}_{
    0.51
    WindowConstants
    0.51
     men
    0.51
    ather
    0.50
     master
    0.50
    rense
    0.50
     marche
    0.49
     tra
    0.47
    Activations Density 2.273%

    No Known Activations