© 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. 4154
    Prev
    Next
    INDEX
    Explanations

    transition words and phrases indicative of reasoning

    oai_token-act-pair · gemini-2.0-flash

    words with specific formatting or styles

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

    Say "for this reason"

    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
     nakalista
    -0.96
    enumi
    -0.93
     AspNetCore
    -0.90
     resourceCulture
    -0.90
    NameInMap
    -0.88
    Билгалдахарш
    -0.87
     autorytatywna
    -0.86
     propOrder
    -0.85
     Wikimedijinoj
    -0.84
     AssemblyProduct
    -0.83
    POSITIVE LOGITS
     مواليد
    0.59
     poffible
    0.58
     becauſe
    0.57
     ſeveral
    0.54
     ſhe
    0.54
     Theſe
    0.51
     againſt
    0.50
     ſhall
    0.48
     sauvages
    0.48
     fufficient
    0.47
    Activations Density 6.392%

    No Known Activations