© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6414
    Prev
    Next
    INDEX
    Explanations

    the word "structure" alone or in combination with "function" or "activity"

    oai_token-act-pair · gemini-2.0-flash

    structure

    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
     consultato
    -0.71
    下载附件
    -0.67
    ंदीखरीदारी
    -0.65
     <=",
    -0.65
    stretch
    -0.60
    webElementXpaths
    -0.60
     stretch
    -0.58
    ChildScrollView
    -0.57
    Oneof
    -0.56
     Préférences
    -0.56
    POSITIVE LOGITS
     AspNetCore
    0.58
    Демографія
    0.55
     sanitaires
    0.52
    IUrlHelper
    0.52
     legales
    0.50
     sportiva
    0.49
    urally
    0.49
    外部链接
    0.47
     illet
    0.47
     metálica
    0.46
    Activations Density 0.712%

    No Known Activations