© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3458
    Prev
    Next
    INDEX
    Explanations

    phrases that imply something momentous is about to end/be completed

    oai_token-act-pair · gemini-2.0-flash

    endings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     متعلقه
    -0.84
    RectangleBorder
    -0.70
    Datuak
    -0.69
    rrggbb
    -0.68
    AccessorTable
    -0.68
    mergeFrom
    -0.67
    ThroughAttribute
    -0.66
     незавершена
    -0.65
     дописавши
    -0.63
     gawas
    -0.63
    POSITIVE LOGITS
    yargs
    0.50
     uintptr
    0.48
    락
    0.44
    ária
    0.44
     useRef
    0.40
     culminating
    0.40
     Prep
    0.40
     Zon
    0.40
    heri
    0.39
     before
    0.39
    Activations Density 1.154%

    No Known Activations