© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10614
    Prev
    Next
    INDEX
    Explanations

    US location names, like cities, states, and counties.

    oai_token-act-pair · gemini-2.0-flash

    geographic locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     STATE
    -0.56
     BoxFit
    -0.56
    state
    -0.54
    State
    -0.54
     freak
    -0.50
    area
    -0.49
    STATE
    -0.49
     popcorn
    -0.49
     freaks
    -0.48
    ffilm
    -0.48
    POSITIVE LOGITS
     <=",
    0.82
    ThroughAttribute
    0.74
     otomatig
    0.65
     الحره
    0.59
    Tikang
    0.58
    invokeLater
    0.57
     تانيه
    0.54
     AssemblyTitle
    0.53
    ibatis
    0.52
     ویکی‌پدی
    0.52
    Activations Density 17.013%

    No Known Activations