© 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. 1692
    Prev
    Next
    INDEX
    Explanations

    plastic or metal materials used for furniture and home improvement.

    oai_token-act-pair · gemini-2.0-flash

    Home and renovation

    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
     Penh
    -0.58
     Indu
    -0.56
    iastes
    -0.55
     initComponents
    -0.55
     שוליים
    -0.55
     indu
    -0.48
    peutic
    -0.47
    Espèce
    -0.47
     seder
    -0.47
    complexType
    -0.46
    POSITIVE LOGITS
     tap
    0.68
     Tap
    0.66
    Tap
    0.65
     taps
    0.62
    tap
    0.58
     TAP
    0.56
    ftagPool
    0.56
    offsetof
    0.56
    TAP
    0.55
     sanitary
    0.54
    Activations Density 1.846%

    No Known Activations