© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12011
    Prev
    Next
    INDEX
    Explanations

    prepositions and terms related to research

    oai_token-act-pair · gemini-2.0-flash

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    $_['
    -0.55
    ViewById
    -0.52
    contentLoaded
    -0.52
    migrationBuilder
    -0.50
     defaultstate
    -0.50
     AssemblyVersion
    -0.50
    MemoryWarning
    -0.49
    кипедия
    -0.46
     &___
    -0.44
    localctx
    -0.44
    POSITIVE LOGITS
    cplusplus
    0.62
    ventory
    0.60
    pright
    0.60
     Portuguesa
    0.59
    assess
    0.59
     nahilalakip
    0.58
    Spesifikasi
    0.58
    hdashline
    0.57
    riage
    0.55
     Приступљено
    0.55
    Activations Density 5.708%

    No Known Activations