© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11283
    Prev
    Next
    INDEX
    Explanations

    code snippets, related to networking, file processing, and web requests

    oai_token-act-pair · gemini-2.0-flash

    Tags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    RepeatedField
    -0.80
    matchCondition
    -0.75
    prüche
    -0.74
    曖昧さ回避
    -0.72
    providedIn
    -0.71
     StatefulWidget
    -0.71
    PerformLayout
    -0.69
    </tbody>
    -0.68
    oredCriteria
    -0.66
     rowspan
    -0.65
    POSITIVE LOGITS
     zelve
    0.73
     mattino
    0.63
     culturelles
    0.62
     automatiques
    0.57
     Anarchy
    0.57
     ISNI
    0.56
     gabbana
    0.55
    رشف
    0.55
     aveug
    0.54
     ſhe
    0.54
    Activations Density 2.458%

    No Known Activations