© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3906
    Prev
    Next
    INDEX
    Explanations

    instances of people making decisions that impact other people, or people being impacted by decisions; it also has a strong affinity for religious and historical references.

    oai_token-act-pair · gemini-2.0-flash

    Thoughts and feelings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    sikt
    -0.46
     thought
    -0.46
     tanke
    -0.45
     plan
    -0.44
     think
    -0.44
     plans
    -0.41
     mind
    -0.38
    Thought
    -0.37
     sasaran
    -0.37
     événements
    -0.36
    POSITIVE LOGITS
    ConstraintMaker
    0.99
    ContentAsync
    0.95
     препратки
    0.92
     InputDecoration
    0.88
    AddTagHelper
    0.87
    Искәрмәләр
    0.85
    rrggbb
    0.84
    AntiForgeryToken
    0.84
    ThroughAttribute
    0.84
     gyhoeddwyd
    0.82
    Activations Density 13.398%

    No Known Activations