© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8691
    Prev
    Next
    INDEX
    Explanations

    words that refer to entities or categories that could be counted or listed

    oai_token-act-pair · gemini-2.0-flash

    spread, spot

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     utafitiHapana
    -0.57
     Manly
    -0.57
    atique
    -0.57
     spol
    -0.55
    atisch
    -0.55
     sven
    -0.52
    flink
    -0.52
     Waren
    -0.52
     Spisak
    -0.52
    omeness
    -0.52
    POSITIVE LOGITS
    qrstuvwxyz
    0.50
     BoxFit
    0.50
    +#+#
    0.48
     GenerationType
    0.46
     UnityEditor
    0.45
     poches
    0.42
     ExecuteAsync
    0.41
     bolsa
    0.41
    iau
    0.41
     InputDecoration
    0.41
    Activations Density 32.017%

    No Known Activations