© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10521
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to the founding, organization, and demise of an entity

    oai_token-act-pair · gemini-2.0-flash

    beginnings and endings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    principalTable
    -0.81
     Савезне
    -0.73
     незавершена
    -0.69
    featureID
    -0.66
    TagMode
    -0.63
     resourceCulture
    -0.63
     <>",
    -0.63
    üyada
    -0.62
    mybatisplus
    -0.62
     utilisons
    -0.62
    POSITIVE LOGITS
     congen
    0.46
     founders
    0.45
     Destin
    0.42
     anivers
    0.41
     Ufer
    0.40
     Reun
    0.39
     Sito
    0.38
    创
    0.38
     foundational
    0.38
     constitu
    0.38
    Activations Density 1.252%

    No Known Activations