© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9819
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and superlatives related to rankings in competitions

    oai_token-act-pair · gemini-2.0-flash

    ordinal numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    はじめに
    -0.68
     WaitForSeconds
    -0.63
    meester
    -0.61
    aspectj
    -0.61
    verwijspagina
    -0.58
    \}}
    -0.58
    ClientSize
    -0.57
     setContent
    -0.57
     jsPsych
    -0.57
     dolayı
    -0.56
    POSITIVE LOGITS
    MigrationBuilder
    0.63
    Datuak
    0.52
     SEDS
    0.50
    UrlResolution
    0.50
    featureID
    0.49
    sidemargin
    0.49
    RepeatedField
    0.47
    XmlAccessType
    0.47
     missing
    0.42
    RUnlock
    0.42
    Activations Density 0.327%

    No Known Activations