© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14755
    Prev
    Next
    INDEX
    Explanations

    initials and periods, often in legal or academic contexts

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     acer
    -0.50
    ViewGroup
    -0.48
    Reparto
    -0.48
    BeginContext
    -0.47
    ahar
    -0.45
    ña
    -0.44
     Essentially
    -0.44
     ...
    -0.43
     ?
    -0.43
     }}}{
    -0.42
    POSITIVE LOGITS
    WireFormatLite
    0.85
    SharedDtor
    0.84
     Савезне
    0.75
     itſelf
    0.72
     EconPapers
    0.69
     intptr
    0.67
    orianCalendar
    0.66
    <bos>
    0.65
     Drapeau
    0.65
    ьаж
    0.64
    Activations Density 4.785%

    No Known Activations