© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15467
    Prev
    Next
    INDEX
    Explanations

    a mix of numbers and punctuation in the text

    oai_token-act-pair · gemini-2.0-flash

    Beginning of text

    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
    AccessorTable
    -0.71
    ⓧ
    -0.66
     Référence
    -0.63
    EDEFAULT
    -0.62
     propOrder
    -0.54
    ंदीखरीदारी
    -0.54
    StoryboardSegue
    -0.54
     transfieras
    -0.53
    isContained
    -0.52
    Tembelea
    -0.52
    POSITIVE LOGITS
    <bos>
    0.64
     PackageManager
    0.49
     đời
    0.46
    byg
    0.43
    MENAFN
    0.42
    zugehen
    0.40
    enerbah
    0.40
    pite
    0.39
    lamy
    0.39
    Literatur
    0.39
    Activations Density 13.112%

    No Known Activations