© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8519
    Prev
    Next
    INDEX
    Explanations

    lines of code containing URLs, especially those starting with "https" and that also contain the word "following."

    oai_token-act-pair · gemini-2.0-flash

    https

    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
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -1.10
    ⓧ
    -0.91
     vectorielles
    -0.85
     alimentaires
    -0.82
     définiti
    -0.80
     mourut
    -0.80
     fermés
    -0.78
     HasFactory
    -0.78
     commerciaux
    -0.76
     relatifs
    -0.74
    POSITIVE LOGITS
     "
    0.53
    kr
    0.48
    rá
    0.46
     .
    0.45
    ing
    0.45
     util
    0.44
     sia
    0.44
     dé
    0.43
     series
    0.43
     system
    0.43
    Activations Density 1.356%

    No Known Activations