© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10098
    Prev
    Next
    INDEX
    Explanations

    words related to abstract concepts and emotions

    oai_token-act-pair · gemini-2.0-flash

    miscellaneous topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     that
    -1.48
     bahwa
    -0.93
     que
    -0.82
     که
    -0.82
    that
    -0.82
     bahawa
    -0.81
     rằng
    -0.80
     dass
    -0.79
     kwamba
    -0.77
     że
    -0.76
    POSITIVE LOGITS
    itres
    0.51
    MENAFN
    0.49
    ValueStyle
    0.49
     ControllerBase
    0.48
     it
    0.47
    Geografía
    0.47
     I
    0.46
     referenties
    0.45
     Municipalidad
    0.44
    versammlung
    0.43
    Activations Density 0.776%

    No Known Activations