© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8267
    Prev
    Next
    INDEX
    Explanations

    parts of a question and answer exchange, including the setup sentences, the answers, and the supporting information the answers refer to

    oai_token-act-pair · gemini-2.0-flash

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ⓘ
    -0.52
    onAttach
    -0.49
    Etimología
    -0.47
    msgTypes
    -0.46
    WireFormat
    -0.46
    PRWEB
    -0.45
     referenties
    -0.44
     figur
    -0.44
    Wondering
    -0.44
    Nesta
    -0.43
    POSITIVE LOGITS
    intenance
    0.72
     florales
    0.68
     vôtre
    0.64
     couverts
    0.63
     dagens
    0.61
     cérami
    0.61
     تانيه
    0.60
     africains
    0.60
     démocr
    0.60
     coloré
    0.60
    Activations Density 1.346%

    No Known Activations