© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2006
    Prev
    Next
    INDEX
    Explanations

    the start of parenthetical phrases, especially quotes and code snippets

    oai_token-act-pair · gemini-2.0-flash

    bracketed elements or annotations

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

    quotation marks

    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
     judicia
    -0.62
     indiví
    -0.62
     cardiovas
    -0.58
     proiect
    -0.58
     zwi
    -0.58
     medel
    -0.58
     któ
    -0.56
     кото
    -0.56
     diffe
    -0.56
     attiv
    -0.56
    POSITIVE LOGITS
    webElementXpaths
    0.87
     typelib
    0.79
    +#+#
    0.74
     NSCoder
    0.73
     Normdatei
    0.73
    enumi
    0.71
     الحره
    0.68
    InjectAttribute
    0.68
     kaarangay
    0.67
     EconPapers
    0.67
    Activations Density 0.200%

    No Known Activations