© 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. 9894
    Prev
    Next
    INDEX
    Explanations

    mentions of United States history from the 1700-1800s along with place names and political terms related to the same eras.

    oai_token-act-pair · gemini-2.0-flash

    place names

    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
    R
    -0.53
    L
    -0.52
    M
    -0.51
    ing
    -0.50
    İY
    -0.49
    g
    -0.48
    l
    -0.48
    r
    -0.46
    class
    -0.46
     R
    -0.45
    POSITIVE LOGITS
    contentLoaded
    0.87
    ViewImports
    0.82
    MessageTagHelper
    0.77
    /−
    0.77
     الرياضيه
    0.75
    ")));
    0.75
     nakalista
    0.75
     Roskov
    0.75
     ]
    0.73
    '}>
    0.72
    Activations Density 32.577%

    No Known Activations