© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7500
    Prev
    Next
    INDEX
    Explanations

    instances of technical writing and scientific research-related terminology

    oai_token-act-pair · gemini-2.0-flash

    technical terminology and keywords

    np_token-act-pair-logits · gpt-4o-mini

    scientific research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    المناصب
    -0.73
    IntoConstraints
    -0.70
    GOTREF
    -0.70
     CURIAM
    -0.63
    ellido
    -0.62
     localObject
    -0.61
     ladri
    -0.56
    ViewFeatures
    -0.55
     femininas
    -0.55
     NSCoder
    -0.54
    POSITIVE LOGITS
    NameInMap
    0.52
     base
    0.50
    Rhestr
    0.49
    sidemargin
    0.49
     Channel
    0.49
    aderos
    0.47
    WireFormat
    0.47
    ṳ
    0.46
    gern
    0.46
    期刊论文
    0.46
    Activations Density 1.082%

    No Known Activations