© 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. 9106
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in legal writing and statutory interpretation.

    oai_token-act-pair · gemini-2.0-flash

    Legal/contractual provisions

    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
     provisions
    -1.59
    provision
    -1.53
     Provisions
    -1.52
     provision
    -1.44
     Provision
    -1.34
     clauses
    -1.30
    Provision
    -1.27
     PROVISIONS
    -1.23
     clause
    -1.19
     provisioning
    -1.04
    POSITIVE LOGITS
     سكانية
    0.63
     समीक्षाओं
    0.60
     vuitton
    0.60
    дцать
    0.49
    unehmen
    0.49
     supra
    0.47
    sser
    0.47
    niająca
    0.47
     kasarigan
    0.46
    สือ
    0.46
    Activations Density 2.933%

    No Known Activations