© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9218
    Prev
    Next
    INDEX
    Explanations

    instances of doors being opened or people looking out windows

    oai_token-act-pair · gemini-2.0-flash

    door

    np_max-act-logits · gemini-2.0-flash

    door

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    AddTagHelper
    -1.06
     StatelessWidget
    -1.00
    contentLoaded
    -0.92
    ViewImports
    -0.86
     StatefulWidget
    -0.86
    expandindo
    -0.78
     InputDecoration
    -0.78
     "..\..\..\
    -0.77
    Tikang
    -0.77
     HasFactory
    -0.76
    POSITIVE LOGITS
    man
    0.39
     mani
    0.38
     stood
    0.38
    OpCode
    0.38
    board
    0.38
     испо
    0.36
     to
    0.35
     frame
    0.35
    eroon
    0.35
     over
    0.35
    Activations Density 3.353%

    No Known Activations