© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10090
    Prev
    Next
    INDEX
    Explanations

    the HTML meta viewport tag and its attributes for defining the viewport

    oai_token-act-pair · gemini-2.0-flash

    Code and markup language

    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
    MENAFN
    -0.68
    omock
    -0.60
     communs
    -0.59
    richTextPanel
    -0.59
    mbol
    -0.56
     compétence
    -0.56
     frequenza
    -0.55
     fréquence
    -0.54
     comunes
    -0.52
    SourceChecksum
    -0.52
    POSITIVE LOGITS
     tartalomajánló
    0.54
     Arund
    0.49
    DllImport
    0.45
     ADI
    0.45
    wapV
    0.44
     monop
    0.42
     XCTest
    0.42
     Malte
    0.42
     sond
    0.42
     』
    0.41
    Activations Density 0.576%

    No Known Activations