© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6344
    Prev
    Next
    INDEX
    Explanations

    supernatural and imaginative concepts, especially magic and weaving

    oai_token-act-pair · gemini-2.0-flash

    magic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    forName
    -0.57
    messageInfo
    -0.57
    存于互联网档案馆
    -0.54
    PMailer
    -0.54
    География
    -0.53
    ThroughAttribute
    -0.53
    BufferException
    -0.52
    intahan
    -0.52
     Philist
    -0.52
     pageContext
    -0.52
    POSITIVE LOGITS
     magic
    2.13
    magic
    1.82
     Magic
    1.78
    Magic
    1.74
     MAGIC
    1.70
     magique
    1.67
     magia
    1.66
     magical
    1.62
     magie
    1.61
    MAGIC
    1.53
    Activations Density 0.602%

    No Known Activations