© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6971
    Prev
    Next
    INDEX
    Explanations

    code snippets (likely Javascript) related to retrieving a quiz, or Java code related to phone number management

    oai_token-act-pair · gemini-2.0-flash

    code punctuations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    jsii
    -0.50
    oneofs
    -0.46
    sal
    -0.46
    )$.
    -0.45
     co
    -0.43
    ball
    -0.43
    bal
    -0.43
    madeus
    -0.43
    Sal
    -0.42
    cak
    -0.41
    POSITIVE LOGITS
    HasForeignKey
    0.67
     متعلقه
    0.66
     للمعارف
    0.65
    RegressionTest
    0.64
    رشف
    0.64
     poveznice
    0.63
    TestMethod
    0.60
    ftagPool
    0.60
     <=",
    0.60
     تانيه
    0.60
    Activations Density 5.581%

    No Known Activations