© 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. 9421
    Prev
    Next
    INDEX
    Explanations

    phrases centered on the word "be" in its various forms.

    oai_token-act-pair · gemini-2.0-flash

    Code elements

    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
    omla
    -0.54
     Manip
    -0.50
    wnie
    -0.50
    Manip
    -0.47
     hạng
    -0.47
    inter
    -0.47
    ufige
    -0.46
     manipulated
    -0.45
     wo
    -0.45
     να
    -0.44
    POSITIVE LOGITS
    IVEREF
    0.71
    DeleteBehavior
    0.67
    aarrggbb
    0.65
    HtmlAttribute
    0.63
    EndContext
    0.62
    onViewCreated
    0.61
    sizeCache
    0.60
    expandindo
    0.59
    +#+#
    0.59
     actionMode
    0.59
    Activations Density 3.822%

    No Known Activations