© 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. 8665
    Prev
    Next
    INDEX
    Explanations

    references to Volkswagen and Skoda cars

    oai_token-act-pair · gemini-2.0-flash

    technical terms and product names

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

    Volkswagen cars

    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
    KommentareTeilen
    -0.56
     Text
    -0.49
     հղումներ
    -0.48
    Text
    -0.41
    bby
    -0.41
    ++++++++
    -0.40
     kasarigan
    -0.40
    لے
    -0.39
     remis
    -0.38
     obst
    -0.37
    POSITIVE LOGITS
    ValueStyle
    0.60
    LookAnd
    0.58
    pinMode
    0.57
     CreateTagHelper
    0.57
     ComVisible
    0.56
    はじめに
    0.56
    ัตว์
    0.56
    tanooga
    0.56
    ksikon
    0.54
    Chham
    0.54
    Activations Density 0.286%

    No Known Activations