© 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. 1888
    Prev
    Next
    INDEX
    Explanations

    Java code snippets, specifically related to JDBC configurations

    oai_token-act-pair · gemini-2.0-flash

    words related to data sources or metadata

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

    Foreign words

    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
    Not in Any Lists

    No Comments

    Negative Logits
    atouille
    -0.61
    ValueStyle
    -0.56
    তে
    -0.54
    ăt
    -0.53
     كومونز
    -0.52
     capo
    -0.52
    verifyException
    -0.51
     menar
    -0.50
    ellyn
    -0.50
    imeni
    -0.50
    POSITIVE LOGITS
    Coordonnées
    0.48
    település
    0.47
     ISNI
    0.44
     CreateTagHelper
    0.43
     himo
    0.42
    войства
    0.42
    ürzen
    0.42
    UrlResolution
    0.41
    клопе
    0.41
     Walkover
    0.41
    Activations Density 0.416%

    No Known Activations