© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10731
    Prev
    Next
    INDEX
    Explanations

    phrases referencing the past, particularly "the day" or "days"

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     days
    -1.57
     Days
    -1.47
    Days
    -1.41
     DAYS
    -1.38
    days
    -1.33
     times
    -1.13
    DAYS
    -1.12
     días
    -0.98
    Times
    -0.94
     Times
    -0.91
    POSITIVE LOGITS
    原始内容存档于
    0.67
    شهاد
    0.62
     xoay
    0.57
    pexpr
    0.57
    writeFieldEnd
    0.54
     AssemblyCulture
    0.53
    Alike
    0.53
    DIPSETTING
    0.52
     hal
    0.52
     OnInit
    0.52
    Activations Density 2.717%

    No Known Activations