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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10353
    Prev
    Next
    INDEX
    Explanations

    legal texts involving court cases

    oai_token-act-pair · gemini-2.0-flash

    Legal documents and cases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    providedIn
    -0.93
    awtextra
    -0.90
    :✨
    -0.79
     convertView
    -0.74
    antMatchers
    -0.73
    AccessorTable
    -0.73
     jadx
    -0.73
    bootstrapcdn
    -0.71
    TestingModule
    -0.71
    DoubleQuotes
    -0.71
    POSITIVE LOGITS
     igenom
    0.60
     ihop
    0.53
     varandra
    0.50
     honom
    0.49
     igång
    0.48
     rencontr
    0.47
     émer
    0.47
     religieuses
    0.46
     trụ
    0.45
     vœux
    0.45
    Activations Density 39.628%

    No Known Activations