© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11831
    Prev
    Next
    INDEX
    Explanations

    references to public works in a community such as trails and buildings.

    oai_token-act-pair · gemini-2.0-flash

    Construction projects

    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
     Петра
    -0.38
     
    -0.38
     G
    -0.37
    Matic
    -0.36
    骨
    -0.36
    眠
    -0.34
     sy
    -0.34
     site
    -0.34
     stress
    -0.33
    直
    -0.33
    POSITIVE LOGITS
    LookAnd
    1.10
     TextAppearance
    1.09
    writeFieldEnd
    0.99
    ंदीखरीदारी
    0.98
    ValueStyle
    0.98
     Efq
    0.94
     purpoſe
    0.91
    SourceChecksum
    0.91
    parsedMessage
    0.86
     reaſon
    0.86
    Activations Density 12.886%

    No Known Activations