© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1950
    Prev
    Next
    INDEX
    Explanations

    words and punctuation that indicate a pause or change in thought within a sentence.

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    はじめに
    -0.74
    Cuz
    -0.61
    Starting
    -0.59
     Starting
    -0.59
    ecause
    -0.58
    cuz
    -0.57
     Sebab
    -0.56
    Personendaten
    -0.55
    ValueGeneration
    -0.54
    cause
    -0.54
    POSITIVE LOGITS
     Infórmanos
    0.65
     what
    0.59
    Diweddarwch
    0.57
    windowFixed
    0.56
    ubehör
    0.55
    EditorBrowsable
    0.53
    bootstrapcdn
    0.52
     PopupWindow
    0.52
    (""));
    0.52
    xelles
    0.52
    Activations Density 6.375%

    No Known Activations