© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2377
    Prev
    Next
    INDEX
    Explanations

    words related to forgiveness, legal proceedings, and leniency

    oai_token-act-pair · gemini-2.0-flash

    legal/formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </thead>
    -0.60
    initComponents
    -0.60
    zerland
    -0.60
    Clik
    -0.59
    IntoConstraints
    -0.59
    Portail
    -0.57
    SpringBootTest
    -0.57
    findpost
    -0.57
    FieldBuilder
    -0.54
    ագրություններ
    -0.53
    POSITIVE LOGITS
     pitié
    0.70
     grazia
    0.65
     soyez
    0.62
     juger
    0.61
    曖昧さ回避
    0.57
     éduc
    0.55
    espèce
    0.54
     granted
    0.54
     veuillez
    0.53
     Folly
    0.53
    Activations Density 0.760%

    No Known Activations