© 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. 9024
    Prev
    Next
    INDEX
    Explanations

    technical language from physics, especially related to semiconductors and electronic states

    oai_token-act-pair · gemini-2.0-flash

    Semiconductor physics

    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
    jsdelivr
    -0.76
    SourceChecksum
    -0.69
    ThroughAttribute
    -0.66
    verifyException
    -0.63
    はじめに
    -0.57
    SOUNDBITE
    -0.56
     propOrder
    -0.56
    StatusOK
    -0.56
    principalColumn
    -0.55
    ulose
    -0.54
    POSITIVE LOGITS
    enumi
    0.50
    ILLUSTR
    0.48
    typeof
    0.47
     rowspan
    0.47
    PyErr
    0.46
     stockholders
    0.46
     estúdio
    0.45
    Organisator
    0.43
     nonatomic
    0.43
    camis
    0.42
    Activations Density 3.925%

    No Known Activations