© 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. 9370
    Prev
    Next
    INDEX
    Explanations

    years, monetary values, and citations, especially those including "19"

    oai_token-act-pair · gemini-2.0-flash

    1940s-1970s

    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
    actionMode
    -0.51
     Morphology
    -0.51
     الحره
    -0.48
    
    -0.46
    bagno
    -0.45
     Divider
    -0.45
     uovo
    -0.45
     matriz
    -0.44
    úsqueda
    -0.43
    webElementXpaths
    -0.43
    POSITIVE LOGITS
    6
    0.76
    5
    0.74
    7
    0.71
    9
    0.65
    4
    0.65
     تضيفلها
    0.65
    8
    0.64
    IBOutlet
    0.62
    1
    0.60
    2
    0.60
    Activations Density 17.319%

    No Known Activations