© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3887
    Prev
    Next
    INDEX
    Explanations

    words and phrases broadly related to sociology, cultural studies, and anthropology.

    oai_token-act-pair · gemini-2.0-flash

    technical terms and concepts related to academic research

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

    Academic text

    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
     compréhen
    -0.54
     concevoir
    -0.52
    \}=\
    -0.50
     storici
    -0.49
     démocr
    -0.48
     Audiodateien
    -0.48
     Ahor
    -0.46
     débats
    -0.46
     découver
    -0.45
     جام
    -0.44
    POSITIVE LOGITS
     propOrder
    0.87
     BoxDecoration
    0.79
    AddTagHelper
    0.74
    EClass
    0.73
    #+#
    0.72
    enity
    0.70
    ParallelGroup
    0.69
    sizeCache
    0.68
    SharedCtor
    0.68
    ConstraintMaker
    0.66
    Activations Density 2.783%

    No Known Activations