© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11337
    Prev
    Next
    INDEX
    Explanations

    stories about people and their beds/bedrooms, especially children or the sick

    oai_token-act-pair · gemini-2.0-flash

    bed and room

    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
     minced
    -0.50
     midfield
    -0.48
    invokeLater
    -0.47
     Sociales
    -0.47
     tangential
    -0.47
     Falkland
    -0.47
     Nauk
    -0.46
    ễn
    -0.46
     Stamp
    -0.45
     Biophys
    -0.45
    POSITIVE LOGITS
     bed
    1.02
    bed
    0.89
     Bed
    0.87
     room
    0.87
     beds
    0.84
    Bed
    0.84
    Double
    0.81
    beds
    0.81
    BED
    0.77
     Beds
    0.77
    Activations Density 0.668%

    No Known Activations