© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1860
    Prev
    Next
    INDEX
    Explanations

    random words, proper nouns, and jargon specific to this document

    oai_token-act-pair · gemini-2.0-flash

    Anton

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    rhein
    -0.52
     acoustics
    -0.52
     prossima
    -0.51
    TagMode
    -0.50
     Vikipedi
    -0.50
     impractica
    -0.48
     Danach
    -0.48
    utschen
    -0.48
     INTERESAR
    -0.47
     équ
    -0.47
    POSITIVE LOGITS
    MethodManager
    0.62
     ExecuteAsync
    0.57
    COUVER
    0.55
     fieldNum
    0.53
     internetowa
    0.53
     saites
    0.50
    下载附件
    0.49
    epik
    0.46
    rån
    0.46
     GenerationType
    0.46
    Activations Density 7.548%

    No Known Activations