© 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. 3814
    Prev
    Next
    INDEX
    Explanations

    mentions of the timing of an event like "onset" and "earlier" along with related words like "date" and "age"

    oai_token-act-pair · gemini-2.0-flash

    age / time progression

    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
    Diwedd
    -0.63
    InitVars
    -0.60
     mergeFrom
    -0.55
    œur
    -0.53
    stination
    -0.52
    setopt
    -0.50
    WithIOException
    -0.49
     AssemblyCulture
    -0.49
     فريبيس
    -0.49
    setCellValue
    -0.49
    POSITIVE LOGITS
     shifted
    0.57
     متعلقه
    0.56
     Fasc
    0.53
     shifting
    0.50
     виправивши
    0.49
     Shift
    0.48
    ItemLayout
    0.48
    PASO
    0.47
    存于互联网档案馆
    0.47
    shifting
    0.47
    Activations Density 2.000%

    No Known Activations