© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 3703
    Prev
    Next
    INDEX
    Explanations

    the names of organizations, especially companies and academic institutions, and words associated with studies.

    oai_token-act-pair · gemini-2.0-flash

    Taxes and legal issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    endphp
    -0.63
     Само
    -0.60
     Pair
    -0.59
     User
    -0.58
    Муж
    -0.56
    User
    -0.56
    Patients
    -0.55
     }}"></
    -0.55
     Você
    -0.55
     Players
    -0.54
    POSITIVE LOGITS
     Legend
    0.62
     Spec
    0.60
    CodeAttribute
    0.60
     Source
    0.56
    énario
    0.55
     Gold
    0.52
     Cream
    0.52
    contentLoaded
    0.51
    Legend
    0.51
    Specialist
    0.50
    Activations Density 6.971%

    No Known Activations