© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7111
    Prev
    Next
    INDEX
    Explanations

    expressions of opinions about political or social issues

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     essai
    -0.52
    المشاركات
    -0.50
    BufferException
    -0.49
    ardt
    -0.49
    SBATCH
    -0.48
    DispatchToProps
    -0.48
     devrez
    -0.47
    ersham
    -0.46
    makeConstraints
    -0.46
    CIN
    -0.46
    POSITIVE LOGITS
    afficheront
    0.84
    WriteBarrier
    0.69
     gyhoeddwyd
    0.60
     midline
    0.60
     intptr
    0.57
     himo
    0.54
     مرئيه
    0.52
    Personensuche
    0.52
    webElementGuid
    0.51
    IndentedString
    0.50
    Activations Density 1.205%

    No Known Activations