© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10204
    Prev
    Next
    INDEX
    Explanations

    a mix of characters and code, possibly from different languages and formats, including monetary symbols and truncated words

    oai_token-act-pair · gemini-2.0-flash

    Russian characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     africains
    -0.54
    <bos>
    -0.52
     démocr
    -0.52
     Numa
    -0.50
     réfugiés
    -0.48
     atsi
    -0.48
    ciate
    -0.47
     atento
    -0.44
     culturelles
    -0.44
     médec
    -0.43
    POSITIVE LOGITS
    — 
    0.94
    Diwedd
    0.83
    DoubleQuotes
    0.82
     contextLoads
    0.78
    NewLabel
    0.76
     getRule
    0.76
    LEncoder
    0.75
    — 
    0.75
    MLLoader
    0.73
     كومونز
    0.73
    Activations Density 2.481%

    No Known Activations