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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10758
    Prev
    Next
    INDEX
    Explanations

    legal documents with references, motions, numbers, laws, and governing bodies

    oai_token-act-pair · gemini-2.0-flash

    Legal/legislative documents

    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
    Bounce
    -0.48
    zewod
    -0.48
     grecque
    -0.47
     TRAP
    -0.46
    __':
    -0.45
     SLIP
    -0.44
    Crawl
    -0.44
     tpu
    -0.44
    umuz
    -0.43
    ">';
    -0.42
    POSITIVE LOGITS
     ujednoznacz
    0.71
     disponibilités
    0.69
    enumii
    0.67
     createState
    0.67
    ագրություններ
    0.62
    Decided
    0.59
     ORDERED
    0.56
     المعيارى
    0.56
    ArgumentParser
    0.56
     rhestr
    0.56
    Activations Density 11.244%

    No Known Activations