© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1159
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the Neopagan Wheel of the Year

    oai_token-act-pair · gemini-2.0-flash

    Pagan holidays and festivals

    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
     calendar
    -1.09
     Calendar
    -0.98
     fiscal
    -0.93
     calendars
    -0.90
    calendar
    -0.90
    fiscal
    -0.88
     CALENDAR
    -0.85
     Fiscal
    -0.82
    Calendar
    -0.81
     kalend
    -0.81
    POSITIVE LOGITS
     onResponse
    0.71
    Portail
    0.68
    thâu
    0.65
     незавершена
    0.62
    OGND
    0.59
     rév
    0.59
     pira
    0.58
    SHIRE
    0.57
    addContainerGap
    0.57
    ERAL
    0.55
    Activations Density 2.199%

    No Known Activations