© 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. 4386
    Prev
    Next
    INDEX
    Explanations

    scientific procedures being performed, often including the word 'was', 'were' or 'by'.

    oai_token-act-pair · gemini-2.0-flash

    Scientific measuring/calculating

    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
    featureID
    -0.57
     infect
    -0.56
     Preferencias
    -0.56
     Putting
    -0.54
     raising
    -0.54
    说什么
    -0.53
    新浪
    -0.52
     venons
    -0.52
     ſtate
    -0.52
    Cyfeiriadau
    -0.52
    POSITIVE LOGITS
     done
    0.62
    StoryboardSegue
    0.57
     StringTokenizer
    0.53
    contentLoaded
    0.52
    IndentedString
    0.50
    PerformLayout
    0.50
     obtained
    0.48
    toHaveBeenCalled
    0.48
    Personensuche
    0.48
     NUKAT
    0.47
    Activations Density 2.313%

    No Known Activations