© 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. 5944
    Prev
    Next
    INDEX
    Explanations

    HTML tags, simple math, and the word "summary"

    oai_token-act-pair · gemini-2.0-flash

    Software/technical context

    np_max-act-logits · gemini-2.0-flash

    markup characters

    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_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
    super
    -1.80
     super
    -1.75
     Super
    -1.31
    Super
    -1.30
     SUPER
    -1.23
    SUPER
    -1.12
     супер
    -1.01
    uper
    -0.98
     súper
    -0.91
    超级
    -0.88
    POSITIVE LOGITS
    SourceChecksum
    0.75
    Geplaatst
    0.71
    wpi
    0.70
    AndroidJUnit
    0.67
    HasAnnotation
    0.67
     estekak
    0.64
     ModelExpression
    0.63
     betweenstory
    0.61
    Tikang
    0.60
    exitRule
    0.60
    Activations Density 2.672%

    No Known Activations