© 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. 9198
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to physical, health and domestic activities

    oai_token-act-pair · gemini-2.0-flash

    Body and health

    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
    новништво
    -0.71
    AndEndTag
    -0.69
    ⋙
    -0.65
    XmlIgnore
    -0.65
    numerusform
    -0.62
    MENAFN
    -0.61
     <<<<<<<<<<<<<<
    -0.60
    TypedDataSet
    -0.59
    ẨM
    -0.59
    ArgumentParser
    -0.58
    POSITIVE LOGITS
    psack
    0.49
     وصلة
    0.44
     Cros
    0.44
     Lothar
    0.44
    CompleteListener
    0.43
     Bios
    0.42
     Macht
    0.41
    icity
    0.41
     umana
    0.41
     passport
    0.41
    Activations Density 2.270%

    No Known Activations