© 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. 4982
    Prev
    Next
    INDEX
    Explanations

    words related to scientific concepts such as cell biology, manufacturing, or academia

    oai_token-act-pair · gemini-2.0-flash

    college

    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
     floor
    -0.87
     surface
    -0.86
     wall
    -0.82
     membrane
    -0.82
    surface
    -0.79
     roof
    -0.74
     shelf
    -0.74
     ceiling
    -0.73
     Floor
    -0.73
    floor
    -0.72
    POSITIVE LOGITS
    makeConstraints
    0.59
    tisseur
    0.56
    InSection
    0.56
    Personendaten
    0.56
    testng
    0.56
    stateProvider
    0.56
     disponibilités
    0.54
     مرئيه
    0.52
    Билгалдахарш
    0.51
     الحره
    0.50
    Activations Density 5.754%

    No Known Activations