© 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. 1817
    Prev
    Next
    INDEX
    Explanations

    content from scientific literature, especially including journal names, figure references, and possibly mathematical formulas

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical vocabulary

    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
     OFDb
    -0.52
    featureID
    -0.38
    RenderAtEndOf
    -0.36
     "..\..\
    -0.34
     Италијани
    -0.34
     يتيمه
    -0.33
     nonUne
    -0.33
     "..\..\..\
    -0.32
    DockStyle
    -0.30
     فريبيس
    -0.30
    POSITIVE LOGITS
    UNEP
    0.68
    MATHEMAT
    0.65
    Transcrip
    0.63
    FTIR
    0.62
     coû
    0.61
    Tensi
    0.60
    Legături
    0.60
     fermés
    0.60
    Cyto
    0.60
     sèche
    0.59
    Activations Density 65.374%

    No Known Activations