© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11433
    Prev
    Next
    INDEX
    Explanations

    words relating to legal proceedings, especially those relating to investigation and evidence

    oai_token-act-pair · gemini-2.0-flash

    legal proceedings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ว่า
    -0.48
    υνα
    -0.44
     Li
    -0.44
     ten
    -0.43
    rag
    -0.42
     ý
    -0.42
     Ch
    -0.41
    itsch
    -0.41
     Pl
    -0.39
     vis
    -0.38
    POSITIVE LOGITS
    GEBURTSDATUM
    1.16
    +#+#
    0.96
     насељу
    0.94
    ArrowToggle
    0.84
    GEBURTS
    0.82
    Portale
    0.78
    prefixer
    0.78
     <<<<<<<<<<<<<<
    0.77
     AssemblyCulture
    0.77
    تقاوى
    0.75
    Activations Density 3.777%

    No Known Activations