© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12107
    Prev
    Next
    INDEX
    Explanations

    academic research papers talking about children and parents

    oai_token-act-pair · gemini-2.0-flash

    children and parents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     womanhood
    -0.82
     Jefus
    -0.73
     manhood
    -0.66
    aughters
    -0.66
     Monfieur
    -0.66
    новништво
    -0.64
    emale
    -0.64
     maschile
    -0.63
    NUMX
    -0.63
     tetrach
    -0.63
    POSITIVE LOGITS
     Lightboxes
    0.48
    protoimpl
    0.47
    SequentialGroup
    0.45
    ViewFeatures
    0.42
    TagHelper
    0.42
     project
    0.41
     Project
    0.40
    ías
    0.39
    stre
    0.39
    Project
    0.39
    Activations Density 2.048%

    No Known Activations