© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12447
    Prev
    Next
    INDEX
    Explanations

    filler words, interjections, and expressions of emotion or acknowledgement, like "hmm", "okay", and laughter.

    oai_token-act-pair · gemini-2.0-flash

    Laughter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    دانشنامهٔ
    -0.52
     idéia
    -0.51
    XmlNode
    -0.48
    "]];
    -0.47
     INVENTION
    -0.47
    ']]
    -0.47
     acaso
    -0.46
     funzion
    -0.46
     nabí
    -0.45
     disegni
    -0.43
    POSITIVE LOGITS
     "..\..\
    0.89
     "..\..\..\
    0.79
    twimg
    0.73
    
    0.71
     Paglinawan
    0.67
     NSCoder
    0.65
    UpInside
    0.60
    IVEREF
    0.59
    webElementXpaths
    0.59
    ]<=
    0.58
    Activations Density 9.961%

    No Known Activations