© 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. 10184
    Prev
    Next
    INDEX
    Explanations

    legal and medical terminology mixed in a context of providing relief

    oai_token-act-pair · gemini-2.0-flash

    Discussing types of relief

    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
     Relief
    -1.53
    Relief
    -1.45
     relief
    -1.44
     RELIEF
    -1.44
    relief
    -1.32
     relieves
    -1.10
     relieving
    -1.09
     alleviation
    -1.06
     alivio
    -1.01
     reliefs
    -1.00
    POSITIVE LOGITS
    Re
    0.51
    Com
    0.49
     Compton
    0.48
     Lisboa
    0.47
     sou
    0.46
     Re
    0.45
    зербай
    0.44
     Com
    0.43
    SpringBootTest
    0.43
     keg
    0.42
    Activations Density 1.900%

    No Known Activations