© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11671
    Prev
    Next
    INDEX
    Explanations

    references to family members and names

    oai_token-act-pair · gemini-2.0-flash

    Family history and biography

    np_max-act-logits · 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
    Not in Any Lists

    No Comments

    Negative Logits
     alimentaires
    -0.59
     démocr
    -0.53
     judiciaire
    -0.52
     aéri
    -0.52
     élev
    -0.49
     automatiques
    -0.46
     économiques
    -0.45
     stratégique
    -0.45
     asiatique
    -0.44
     démocratique
    -0.43
    POSITIVE LOGITS
     AssemblyTitle
    1.09
    featureID
    0.79
    KommentareTeilen
    0.79
     MainAxisSize
    0.78
     resultCode
    0.73
    abestanden
    0.72
    SuppressMessage
    0.71
    aarrggbb
    0.71
     Minnie
    0.71
    PerformLayout
    0.70
    Activations Density 3.111%

    No Known Activations