© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6742
    Prev
    Next
    INDEX
    Explanations

    uses of the words "that", "was", and "time", referring to the specific period when talking about something

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    signable
    -0.65
    曖昧さ回避
    -0.62
     viewDidLoad
    -0.54
    inguish
    -0.47
    ientôt
    -0.47
    PRIME
    -0.46
    Билгалдахарш
    -0.46
    cdk
    -0.46
     midterm
    -0.45
    unehmen
    -0.45
    POSITIVE LOGITS
    IContainer
    0.73
    SourceChecksum
    0.72
    లాలు
    0.66
     existence
    0.62
     existed
    0.59
     esteve
    0.59
     ModelExpression
    0.56
     séjour
    0.56
    adə
    0.56
     stayed
    0.56
    Activations Density 1.372%

    No Known Activations