© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12972
    Prev
    Next
    INDEX
    Explanations

    content dealing with how to reduce home energy usage and the history of curtains

    oai_token-act-pair · gemini-2.0-flash

    non-standard tokens or symbols

    np_token-act-pair-logits · gpt-4o-mini

    Curtains and doors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Metcalf
    -0.54
     Doors
    -0.48
     Türen
    -0.47
    ũng
    -0.47
     doors
    -0.47
    InputTagHelper
    -0.46
    setPage
    -0.46
     Limoges
    -0.45
    azzi
    -0.45
     ternary
    -0.45
    POSITIVE LOGITS
    GEBURTSDATUM
    0.81
    ########.
    0.80
    ⓧ
    0.79
    клопе
    0.69
    Viitteet
    0.68
    verwijspagina
    0.66
    rungsseite
    0.65
    ImageContext
    0.61
    #+#
    0.60
    (!__
    0.60
    Activations Density 1.327%

    No Known Activations