© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11048
    Prev
    Next
    INDEX
    Explanations

    what appear to be non-words from different contexts, including codes, math symbols, and spelling errors

    oai_token-act-pair · gemini-2.0-flash

    Code output

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     estimés
    -1.03
    MigrationBuilder
    -1.00
    Билгалдахарш
    -0.99
    archiviato
    -0.98
    contentLoaded
    -0.94
    SourceChecksum
    -0.91
    ьаж
    -0.90
    httphttps
    -0.89
     متعلقه
    -0.88
    dafx
    -0.87
    POSITIVE LOGITS
    >
    0.41
    ll
    0.40
    ui
    0.35
    ar
    0.35
     wers
    0.34
    <
    0.34
    os
    0.34
    n
    0.33
    ice
    0.31
    ver
    0.31
    Activations Density 3.916%

    No Known Activations