© 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. 6573
    Prev
    Next
    INDEX
    Explanations

    the start of questions in first person

    oai_token-act-pair · gemini-2.0-flash

    I/you

    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
    orElse
    -0.55
    WebElementEntity
    -0.53
    MessageOf
    -0.52
    ViewChild
    -0.52
     sí
    -0.49
    apimachinery
    -0.48
     Meanwhile
    -0.46
    richTextPanel
    -0.46
    typeorm
    -0.45
    zkod
    -0.45
    POSITIVE LOGITS
     commerciaux
    0.74
     commerciales
    0.66
    ImageContext
    0.62
    AutoresizingMask
    0.59
     âgées
    0.58
    Referencie
    0.56
     MessageBoxIcon
    0.55
     nahilalakip
    0.54
    cleros
    0.53
    ChildScrollView
    0.52
    Activations Density 4.101%

    No Known Activations