© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3348
    Prev
    Next
    INDEX
    Explanations

    what appears to be multiple things including abbreviations, code fragments, medical terms, and violence.

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     remote
    -0.62
    
    -0.60
    osoba
    -0.60
    shi
    -0.58
     Remote
    -0.55
    wab
    -0.54
    Remote
    -0.54
     shi
    -0.52
    ycznej
    -0.50
    remote
    -0.50
    POSITIVE LOGITS
    RenderAtEndOf
    0.66
    rungsseite
    0.61
    MemoryWarning
    0.59
    Tikang
    0.59
    FunctionFlags
    0.55
     librarians
    0.52
    Hentet
    0.51
     MessageBoxIcon
    0.50
    Encyclopædia
    0.49
    RefNanny
    0.49
    Activations Density 8.985%

    No Known Activations