© 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. 4667
    Prev
    Next
    INDEX
    Explanations

    a variety of terms mostly related to commerce, art, and personal fulfillment.

    oai_token-act-pair · gemini-2.0-flash

    blog post snippets

    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
    URLException
    -0.71
     itſelf
    -0.56
    anasia
    -0.56
    esgue
    -0.56
    LoggerFactory
    -0.55
     RIPRODUZIONE
    -0.54
    partimento
    -0.54
    ElementException
    -0.52
    ıştır
    -0.52
    ſelves
    -0.52
    POSITIVE LOGITS
     you
    0.73
    principalTable
    0.67
     we
    0.65
     مرئيه
    0.62
    
    0.61
    kloped
    0.59
    ंदीखरीदारी
    0.57
     lenker
    0.57
    migrationBuilder
    0.54
     disponibilités
    0.54
    Activations Density 7.984%

    No Known Activations