© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12654
    Prev
    Next
    INDEX
    Explanations

    words related to locations or people within medical or business fields

    oai_token-act-pair · gemini-2.0-flash

    front reception

    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
    发表于
    -0.71
    AccessorTable
    -0.69
    JspWriter
    -0.61
     pinulongan
    -0.59
    WireFormatLite
    -0.58
    HttpPut
    -0.58
    PerformLayout
    -0.57
    </tfoot>
    -0.54
    fillType
    -0.52
    AddAttribute
    -0.52
    POSITIVE LOGITS
     reception
    1.32
     front
    1.28
    front
    1.10
    reception
    1.09
     Reception
    1.09
     Front
    1.08
    Front
    1.08
    Reception
    1.07
    FRONT
    1.00
     recepción
    0.99
    Activations Density 0.529%

    No Known Activations