© 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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 118
    Prev
    Next
    INDEX
    Explanations

    lines of computer code that contain the word "maxOccurs" and the word "datatype"

    oai_token-act-pair · gemini-2.0-flash

    max

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ">//
    -0.52
     Diſ
    -0.52
     بيها
    -0.47
    abancı
    -0.47
    ſelf
    -0.47
    })->
    -0.47
    ,:),
    -0.44
    boxylic
    -0.42
     transfieras
    -0.42
    зади
    -0.42
    POSITIVE LOGITS
     kasarigan
    0.75
     invokingState
    0.70
    ISupport
    0.68
     InputDecoration
    0.67
    IsContent
    0.61
    XMLSchema
    0.60
    خصة
    0.59
     שוליים
    0.58
     ContentValues
    0.57
    ginfo
    0.56
    Activations Density 1.307%

    No Known Activations