© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11029
    Prev
    Next
    INDEX
    Explanations

    mentions of "Star Wars" and related terms.

    oai_token-act-pair · gemini-2.0-flash

    star wars and space

    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
     initComponents
    -0.93
    rungsseite
    -0.79
     Force
    -0.76
    httphttps
    -0.74
     ostavi
    -0.74
    SequentialGroup
    -0.73
    tonsoft
    -0.72
     estekak
    -0.70
    Abit
    -0.68
    tvguidetime
    -0.68
    POSITIVE LOGITS
     solare
    0.38
    dak
    0.37
     συ
    0.36
    TV
    0.36
    _{+}
    0.36
     économies
    0.35
     engraçadas
    0.35
    alic
    0.35
    rão
    0.35
    Henri
    0.34
    Activations Density 0.533%

    No Known Activations