© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7034
    Prev
    Next
    INDEX
    Explanations

    monetary amounts, organizations with capitalized names, and quotes from people.

    oai_token-act-pair · gemini-2.0-flash

    financial reports

    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
     "
    -0.77
    NUMX
    -0.61
    träge
    -0.59
    We
    -0.58
    RegistryLite
    -0.57
     ansatte
    -0.57
     tredje
    -0.57
     "[
    -0.56
     “
    -0.55
    CURLOPT
    -0.55
    POSITIVE LOGITS
    abetes
    0.55
    ContentAsync
    0.54
     <=",
    0.51
    psum
    0.49
    LEncoder
    0.49
    RTEX
    0.49
     Вікіпе
    0.48
     للمعارف
    0.47
     cannot
    0.47
    createStatement
    0.47
    Activations Density 6.836%

    No Known Activations