© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10045
    Prev
    Next
    INDEX
    Explanations

    words related to life experiences and color

    oai_token-act-pair · gemini-2.0-flash

    emotions, characteristics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    氓
    -0.54
    τοι
    -0.52
    VersionUID
    -0.52
    icoot
    -0.49
     democrática
    -0.49
     secrecy
    -0.49
     abband
    -0.49
     XCTest
    -0.48
     deschis
    -0.47
    tador
    -0.46
    POSITIVE LOGITS
     emotion
    0.85
     list
    0.85
     feature
    0.76
     flavor
    0.73
    list
    0.68
    feature
    0.68
     expression
    0.65
     flavour
    0.63
     ap
    0.63
    flavor
    0.63
    Activations Density 2.717%

    No Known Activations