© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 12984
    Prev
    Next
    INDEX
    Explanations

    words related to technical writing or descriptions, including patents

    oai_token-act-pair · gemini-2.0-flash

    sentence start words

    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
     Rail
    -0.71
     Forest
    -0.69
     Fleet
    -0.68
     Farm
    -0.67
     Bank
    -0.65
     Medal
    -0.64
     Chamber
    -0.64
     Road
    -0.64
     House
    -0.63
     Ball
    -0.63
    POSITIVE LOGITS
     Then
    1.29
     Also
    1.27
     Because
    1.25
     That
    1.22
     When
    1.21
     There
    1.21
     This
    1.21
     Which
    1.20
     These
    1.20
     They
    1.20
    Activations Density 56.950%

    No Known Activations