© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13374
    Prev
    Next
    INDEX
    Explanations

    words referring to humidifiers and the process by which they function

    oai_token-act-pair · gemini-2.0-flash

    ifiers

    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
    Negative Logits
     trebui
    -0.50
     termica
    -0.48
     demurrer
    -0.46
     acorns
    -0.46
     exemplu
    -0.46
     quarry
    -0.46
     MaterialApp
    -0.46
     opio
    -0.46
    count
    -0.45
     utafitiHapana
    -0.45
    POSITIVE LOGITS
     يتيمه
    0.71
     ComVisible
    0.69
    SerializedSize
    0.66
    WireFormatLite
    0.61
    Kariera
    0.59
    BagConstraints
    0.59
    tagHelper
    0.56
     صوتيه
    0.55
    庁
    0.55
    commissioned
    0.54
    Activations Density 0.265%

    No Known Activations