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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16269
    Prev
    Next
    INDEX
    Explanations

    technical words used in medical contexts

    oai_token-act-pair · gemini-2.0-flash

    medical procedures

    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
     nakalista
    -0.58
     ligiloj
    -0.57
     Diaspora
    -0.55
     Vign
    -0.54
     feminino
    -0.53
     Limoges
    -0.52
    toid
    -0.52
     paramInt
    -0.51
     препратки
    -0.50
    SqlClient
    -0.50
    POSITIVE LOGITS
    MessageOf
    0.57
    Datuak
    0.50
     preocupes
    0.49
    ایه
    0.49
    endpush
    0.48
     pinulongan
    0.48
    BeginInit
    0.48
    epiece
    0.47
    ScopeManager
    0.47
     يتيمه
    0.47
    Activations Density 2.499%

    No Known Activations