© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15655
    Prev
    Next
    INDEX
    Explanations

    a combination of contact information, dates, and references to fair use and legal actions.

    oai_token-act-pair · gemini-2.0-flash

    email/website addresses

    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
     elä
    -0.65
     écl
    -0.64
     varandra
    -0.60
     visuales
    -0.57
     väli
    -0.57
     vandens
    -0.57
     ögon
    -0.57
     nė
    -0.57
     cérami
    -0.56
     frequenza
    -0.56
    POSITIVE LOGITS
     thomas
    0.56
     karl
    0.55
     antonio
    0.52
     miguel
    0.52
    JoinColumn
    0.52
     stav
    0.51
     tuesday
    0.51
     kant
    0.51
     god
    0.51
     tomas
    0.51
    Activations Density 11.759%

    No Known Activations