© 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. 4842
    Prev
    Next
    INDEX
    Explanations

    words that signal contrast or concession

    oai_token-act-pair · gemini-2.0-flash

    transition statements

    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
    +#+#
    -0.91
    makeConstraints
    -0.78
    ագրություններ
    -0.77
    MessageTagHelper
    -0.77
     viewDidLoad
    -0.77
    TintMode
    -0.75
    TagHelper
    -0.74
     BorderRadius
    -0.71
     متعلقه
    -0.71
    awtextra
    -0.70
    POSITIVE LOGITS
     بلکه
    0.43
    mdash
    0.40
    անոթ
    0.38
     NLI
    0.38
    เลย
    0.36
     }}-
    0.36
    …,
    0.36
    diyesi
    0.36
     Приступљено
    0.36
    %\[
    0.36
    Activations Density 48.776%

    No Known Activations