© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10107
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to communication via conferences and written form

    oai_token-act-pair · gemini-2.0-flash

    conference/concept

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Хьажоргаш
    -0.94
    :✨
    -0.87
    WriteTagHelper
    -0.84
    хьтан
    -0.83
     ModelExpression
    -0.79
    دانشنامهٔ
    -0.77
    +#+
    -0.75
    GMENT
    -0.72
    ंदीखरीदारी
    -0.71
    aarrggbb
    -0.69
    POSITIVE LOGITS
     bé
    0.50
    <bos>
    0.48
     Drit
    0.45
     ties
    0.45
     gial
    0.42
     گ
    0.42
     Termin
    0.40
    tied
    0.40
    ly
    0.39
    less
    0.39
    Activations Density 20.847%

    No Known Activations