© 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. 13420
    Prev
    Next
    INDEX
    Explanations

    scientific and political discussions related to environment and health risks

    oai_token-act-pair · gemini-2.0-flash

    chemical topics

    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
     chemical
    -2.53
     Chemical
    -2.41
    Chemical
    -2.31
    chemical
    -2.16
     CHEMICAL
    -2.14
    CHEMICAL
    -1.98
     chemically
    -1.95
     Chemicals
    -1.92
     chemistry
    -1.91
     chemicals
    -1.85
    POSITIVE LOGITS
    DrawerToggle
    0.65
    Frame
    0.51
     AppDelegate
    0.50
    RegressionTest
    0.49
    frame
    0.48
    atguigu
    0.48
    rayage
    0.48
    StrictMode
    0.47
     alumínio
    0.47
     []:
    0.46
    Activations Density 4.002%

    No Known Activations