© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10764
    Prev
    Next
    INDEX
    Explanations

    sentences containing a passive voice construction

    oai_token-act-pair · gemini-2.0-flash

    "has been" construction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ContentAsync
    -0.66
     CreateTagHelper
    -0.60
    原始内容存档于
    -0.56
    PyErr
    -0.50
    mpions
    -0.49
     مشين
    -0.48
    IsContent
    -0.48
    onda
    -0.48
    XmlAccessType
    -0.45
    存于互联网档案馆
    -0.45
    POSITIVE LOGITS
    tiéndose
    0.64
     asemenea
    0.62
     étant
    0.61
    تفصیلات
    0.59
     semej
    0.56
     precisione
    0.54
     pauvres
    0.53
     frequenza
    0.52
    richTextPanel
    0.52
     gjerne
    0.52
    Activations Density 10.919%

    No Known Activations