© 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. 10177
    Prev
    Next
    INDEX
    Explanations

    the number 2, often followed by other digits

    oai_token-act-pair · gemini-2.0-flash

    2

    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
    tahui
    -0.58
    +#+
    -0.56
    PerformLayout
    -0.56
    ύ
    -0.52
    έα
    -0.52
     iconTwitter
    -0.51
    IVEREF
    -0.51
    --;
    -0.51
    RenderAtEndOf
    -0.51
     Narendra
    -0.50
    POSITIVE LOGITS
    脚注の使い方
    0.53
    eleste
    0.52
    MetaType
    0.50
    StoreMessageInfo
    0.49
     odkazy
    0.48
    المناصب
    0.47
     auroit
    0.46
     hyvin
    0.46
     expériment
    0.46
    RegressionTest
    0.46
    Activations Density 0.241%

    No Known Activations