© 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. 1119
    Prev
    Next
    INDEX
    Explanations

    words and phrases frequently associated with legal proceedings and financial compensation for damages

    oai_token-act-pair · gemini-2.0-flash

    legal damages

    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
     gynhyrchwyd
    -0.66
     समीक्षाएं
    -0.59
     EconPapers
    -0.57
     cherchés
    -0.56
    NameInMap
    -0.56
     himo
    -0.56
    abetes
    -0.56
    makeConstraints
    -0.55
    MessageOf
    -0.54
    SafeMath
    -0.53
    POSITIVE LOGITS
     cref
    0.57
    الإنجليزية
    0.52
     Soler
    0.50
    hender
    0.50
    żli
    0.48
    JvmStatic
    0.47
    Виды
    0.45
     onBackPressed
    0.45
     Erst
    0.45
     Eligibility
    0.45
    Activations Density 8.654%

    No Known Activations