© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8498
    Prev
    Next
    INDEX
    Explanations

    questions starting with the word "why" in documents that might also contain the word "document"

    oai_token-act-pair · gemini-2.0-flash

    Why

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    mybatisplus
    -0.99
     kasarigan
    -0.88
    XmlAccessType
    -0.75
     henvisninger
    -0.73
     transférez
    -0.72
    mainloop
    -0.71
     J
    -0.69
    Referanser
    -0.69
     the
    -0.68
     The
    -0.68
    POSITIVE LOGITS
     Efq
    1.15
     fhew
    1.11
     purpoſe
    1.09
     raiſ
    1.09
     myſelf
    1.06
     uſe
    1.05
     auffi
    1.04
     Monfieur
    1.04
     uſed
    1.03
     Theſe
    1.02
    Activations Density 1.013%

    No Known Activations