© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6346
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to conflict, politics, bands, medicine or religion

    oai_token-act-pair · gemini-2.0-flash

    strike and literature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     strike
    -0.71
     literature
    -0.52
     Strike
    -0.52
    strike
    -0.50
     strikes
    -0.48
    dist
    -0.46
    we
    -0.46
    Strike
    -0.46
    Literature
    -0.44
     Literature
    -0.43
    POSITIVE LOGITS
    XmlAccessType
    0.96
    MessageTagHelper
    0.94
    aarrggbb
    0.90
    MLLoader
    0.88
    StoryboardSegue
    0.85
    ftagPool
    0.85
     autorytatywna
    0.81
    ArrowToggle
    0.81
    Jegyzetek
    0.80
     Anſ
    0.79
    Activations Density 9.057%

    No Known Activations