© 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. 1957
    Prev
    Next
    INDEX
    Explanations

    numbers, especially those representing quantities or measurements

    oai_token-act-pair · gemini-2.0-flash

    scientific reports' details

    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
     
    -0.29
     Majefty
    -0.27
     B
    -0.27
    0
    -0.26
    8
    -0.25
    ↵
    -0.24
    3
    -0.24
    1
    -0.24
    9
    -0.23
     I
    -0.23
    POSITIVE LOGITS
    NameInMap
    0.90
    UserScript
    0.88
     kasarigan
    0.86
    MigrationBuilder
    0.84
     المعيارى
    0.82
    rungsseite
    0.81
     تضيفلها
    0.79
    expandindo
    0.78
     مشين
    0.78
    ंदीखरीदारी
    0.78
    Activations Density 13.139%

    No Known Activations