© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 453
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    Court/legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     continue
    -0.66
    continue
    -0.65
     continues
    -0.59
     continuation
    -0.58
     Continue
    -0.57
     continuing
    -0.56
     continuance
    -0.55
     retain
    -0.54
    Continue
    -0.53
    ardless
    -0.52
    POSITIVE LOGITS
    adaptiveStyles
    0.61
     autorytatywna
    0.59
     carried
    0.57
    leaves
    0.57
     leaves
    0.57
    SpringBootTest
    0.56
    NoSuchAlgorithm
    0.56
    )))),
    0.56
    done
    0.54
    ModelSerializer
    0.54
    Activations Density 4.857%

    No Known Activations