© 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. 13142
    Prev
    Next
    INDEX
    Explanations

    mentions of the passage of time, marked by words like "last", "past", and "years"

    oai_token-act-pair · gemini-2.0-flash

    time

    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
     myſelf
    -0.91
     himſelf
    -0.84
     uſed
    -0.81
     themſelves
    -0.73
     itſelf
    -0.71
     ſeveral
    -0.70
     poffe
    -0.69
     chofe
    -0.69
     ſever
    -0.68
    ziasztok
    -0.67
    POSITIVE LOGITS
    ChildScrollView
    0.50
    blich
    0.45
     ими
    0.45
    atguigu
    0.45
     op
    0.40
     nhiên
    0.40
    anaf
    0.40
     cal
    0.39
     Cal
    0.39
     global
    0.39
    Activations Density 12.252%

    No Known Activations