© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7323
    Prev
    Next
    INDEX
    Explanations

    the words "the", "film", and the names of film actors

    oai_token-act-pair · gemini-2.0-flash

    Entrepreneurship/performance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    IndentedString
    -0.66
    XmlRootElement
    -0.61
     ویکی‌پدیای
    -0.60
     Alembic
    -0.60
    ItemLayout
    -0.59
     esternos
    -0.59
    IsContent
    -0.57
     gainera
    -0.55
    vieja
    -0.55
    WillAppear
    -0.54
    POSITIVE LOGITS
    etheless
    0.58
    DropTable
    0.52
    elemField
    0.52
     Urqu
    0.48
    WaitGroup
    0.46
     trajets
    0.46
    rigo
    0.45
     Pollack
    0.45
    ikir
    0.44
    DataSetChanged
    0.44
    Activations Density 2.202%

    No Known Activations