© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4229
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to government, politics, or law, especially concerning the Danish or US constitution.

    oai_token-act-pair · gemini-2.0-flash

    legal and government 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_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
    Not in Any Lists

    No Comments

    Negative Logits
     Constitutional
    -1.53
     constitutional
    -1.53
     compressed
    -1.39
    Cons
    -1.39
     compression
    -1.34
    cons
    -1.30
     CONSTITUTION
    -1.30
     constitution
    -1.29
     Cons
    -1.28
     compress
    -1.24
    POSITIVE LOGITS
     članak
    0.53
     lạc
    0.52
    eira
    0.52
    setViewName
    0.50
    scalatest
    0.49
    jera
    0.49
     nonUne
    0.48
    estay
    0.47
    PerformLayout
    0.47
     PAINT
    0.47
    Activations Density 4.784%

    No Known Activations