© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1686
    Prev
    Next
    INDEX
    Explanations

    SQL code snippets, specifically references to 'column' and 'player' within SQL queries

    oai_token-act-pair · gemini-2.0-flash

    specific database column-related variables

    np_token-act-pair-logits · gpt-4o-mini

    Code and SQL queries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    reportWebVitals
    -0.59
     Roskov
    -0.55
     OnDestroy
    -0.52
     incomplète
    -0.52
    \{\\
    -0.50
    flink
    -0.50
    AddRef
    -0.49
    enderror
    -0.49
     recevrez
    -0.48
    ietf
    -0.48
    POSITIVE LOGITS
    Rhestr
    0.63
    UnusedPrivate
    0.62
     Majefty
    0.60
    出版年
    0.59
    LLocation
    0.59
    esModule
    0.59
    WriteTagHelper
    0.57
     Houſe
    0.54
     Jefus
    0.53
     Viceroy
    0.53
    Activations Density 0.338%

    No Known Activations