© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 11212
    Prev
    Next
    INDEX
    Explanations

    the word "is" or the phrase "this event is being held"

    oai_token-act-pair · gemini-2.0-flash

    "to be"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Tr
    -0.45
    at
    -0.44
    WithMany
    -0.42
    we
    -0.40
    他对
    -0.39
    lawan
    -0.39
    addAll
    -0.36
     gặp
    -0.35
    icznej
    -0.35
    ag
    -0.35
    POSITIVE LOGITS
     leſs
    0.85
     purpoſe
    0.81
     ExecuteAsync
    0.81
     itſelf
    0.81
    Lähteet
    0.81
     uſed
    0.80
     fhould
    0.79
     Diſ
    0.78
     Normdatei
    0.77
    ItemBackground
    0.77
    Activations Density 1.042%

    No Known Activations