© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 14029
    Prev
    Next
    INDEX
    Explanations

    the word "concept."

    oai_token-act-pair · gemini-2.0-flash

    concept

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     concepts
    -1.47
     Concepts
    -1.31
    concepts
    -1.27
    Concepts
    -1.20
     CONCEPTS
    -1.11
    Concept
    -1.05
     conceptos
    -1.02
     ideas
    -1.02
     Concept
    -0.98
     Ideas
    -0.95
    POSITIVE LOGITS
    mogat
    0.58
     idea
    0.58
    CROSSTALK
    0.53
    erweise
    0.52
    athione
    0.51
     Lleva
    0.50
     parlant
    0.50
    Linki
    0.50
    úrese
    0.50
    bildung
    0.49
    Activations Density 1.289%

    No Known Activations