© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13149
    Prev
    Next
    INDEX
    Explanations

    various mentions of Microsoft and its Windows and phone products

    oai_token-act-pair · gemini-2.0-flash

    Windows

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    NameInMap
    -0.79
    AccessorTable
    -0.62
    IsMutable
    -0.57
     CreateTagHelper
    -0.56
     ujednoznacz
    -0.54
     ModelExpression
    -0.54
    usercontent
    -0.52
    AlterField
    -0.50
    __*/
    -0.49
     unknownFields
    -0.49
    POSITIVE LOGITS
    Skocz
    0.70
    NUMX
    0.60
     للمعارف
    0.58
    })->
    0.56
    tvguidetime
    0.54
    exels
    0.54
    Referències
    0.52
     Nebel
    0.52
     personali
    0.52
     Deane
    0.52
    Activations Density 0.225%

    No Known Activations