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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11035
    Prev
    Next
    INDEX
    Explanations

    legal terminology, particularly terms related to lawsuits, courts, and judgements.

    oai_token-act-pair · gemini-2.0-flash

    lawsuit

    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
    ніципа
    -0.67
    meneu
    -0.58
     aapt
    -0.57
     Italijani
    -0.57
     BorderRadius
    -0.56
     incomplète
    -0.56
    enumi
    -0.55
     referrerpolicy
    -0.55
    RenderAtEndOf
    -0.54
     Gamb
    -0.53
    POSITIVE LOGITS
     before
    0.76
    before
    0.71
     Before
    0.63
    Personendaten
    0.63
    Before
    0.63
    BEFORE
    0.63
     BEFORE
    0.62
     przed
    0.58
    Населення
    0.55
    PreExecute
    0.53
    Activations Density 4.796%

    No Known Activations