© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5639
    Prev
    Next
    INDEX
    Explanations

    code snippets that are using the semicolon character

    oai_token-act-pair · gemini-2.0-flash

    semicolon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    :✨
    -0.73
    enderror
    -0.59
     nahilalakip
    -0.58
    хьтан
    -0.54
    apimachinery
    -0.47
    unchecked
    -0.46
     Paglinawan
    -0.46
    webElementXpaths
    -0.44
    RTEE
    -0.44
    eleste
    -0.43
    POSITIVE LOGITS
    SequentialGroup
    0.65
    NOPQRST
    0.60
    IBOutlet
    0.58
     whoſe
    0.57
     стоковое
    0.56
     وتسجيلات
    0.56
     Keim
    0.55
    genza
    0.54
     reaſon
    0.54
    csolódó
    0.54
    Activations Density 3.881%

    No Known Activations