© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12783
    Prev
    Next
    INDEX
    Explanations

    sections of text that appear to be programmatically generated lists of items with inconsistent spacing

    oai_token-act-pair · gemini-2.0-flash

    Formatted data

    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
     neceff
    -0.49
     houſe
    -0.48
     ſch
    -0.47
     wed
    -0.47
     tricolor
    -0.47
     étoit
    -0.45
     meridian
    -0.45
     quæ
    -0.45
    parsedMessage
    -0.45
    енча
    -0.44
    POSITIVE LOGITS
    CloseOperation
    0.67
    nessy
    0.59
    lossians
    0.55
     Walkover
    0.54
    mitives
    0.54
     fotográfica
    0.53
    chaffenheit
    0.53
    apeake
    0.52
    zic
    0.52
    Hauptartikel
    0.52
    Activations Density 0.560%

    No Known Activations