© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9360
    Prev
    Next
    INDEX
    Explanations

    words relating to physical accidents and their aftermaths

    oai_token-act-pair · gemini-2.0-flash

    sudden movements/impacts

    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
     Swing
    -0.72
    reportWebVitals
    -0.66
    swing
    -0.64
    GHIJKLM
    -0.63
    Swing
    -0.63
     swing
    -0.62
     swinging
    -0.60
     linkovi
    -0.59
     swings
    -0.58
    BeginInit
    -0.58
    POSITIVE LOGITS
    Климат
    0.53
     Grote
    0.51
     يتيمه
    0.50
     w
    0.49
    ListBox
    0.46
     Islands
    0.46
     quitt
    0.43
    葩
    0.43
     ljus
    0.43
     Oud
    0.41
    Activations Density 4.518%

    No Known Activations