© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13278
    Prev
    Next
    INDEX
    Explanations

    code-related text and text discussing money and flying, possibly related to costs

    oai_token-act-pair · gemini-2.0-flash

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    CloseOperation
    -0.86
     ويكيميديا
    -0.78
    __":
    -0.73
     Wikispecies
    -0.72
    amation
    -0.71
    Corruption
    -0.68
     ChromeDriver
    -0.68
    المناصب
    -0.67
    下载附件
    -0.67
    Referencoj
    -0.66
    POSITIVE LOGITS
     Jefus
    1.02
     becauſe
    0.96
     itſelf
    0.96
    <bos>
    0.96
     ſeveral
    0.94
     whoſe
    0.90
     uſed
    0.90
     himſelf
    0.89
     themſelves
    0.88
     purpoſe
    0.88
    Activations Density 0.989%

    No Known Activations