© 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. 7742
    Prev
    Next
    INDEX
    Explanations

    words from academic papers, especially medical or health-related research

    oai_token-act-pair · gemini-2.0-flash

    Period

    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
     understanding
    -0.57
     factors
    -0.53
     lecteur
    -0.53
     studies
    -0.53
     equalTo
    -0.52
    ECONDS
    -0.52
    Читати
    -0.51
    ця
    -0.50
     adaptive
    -0.50
     behavioral
    -0.50
    POSITIVE LOGITS
    Her
    0.59
     Her
    0.54
    ControllerAdvice
    0.49
    AddTagHelper
    0.48
    strona
    0.47
    GraphicsUnit
    0.47
    úrate
    0.47
    ManagedBean
    0.45
    قایناقلار
    0.45
    概要
    0.44
    Activations Density 11.605%

    No Known Activations