© 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. 7055
    Prev
    Next
    INDEX
    Explanations

    a mix of numbers and math or scientific notation often in the context of genetics and biology

    oai_token-act-pair · gemini-2.0-flash

    Code and notation

    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
    kes
    -0.65
    ked
    -0.63
    k
    -0.61
    ki
    -0.60
    kę
    -0.60
    kus
    -0.60
    ks
    -0.60
    ke
    -0.60
    kd
    -0.59
    ken
    -0.59
    POSITIVE LOGITS
    ValueStyle
    0.68
    Gambas
    0.54
    NameInMap
    0.47
    twimg
    0.47
    Spoljašnje
    0.45
     /\.
    0.45
     تضيفلها
    0.44
     Normdatei
    0.44
    wegg
    0.44
    TagMode
    0.43
    Activations Density 1.854%

    No Known Activations