© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8675
    Prev
    Next
    INDEX
    Explanations

    mentions of "day" in various contexts, including weather, travel, and time

    oai_token-act-pair · gemini-2.0-flash

    day

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     day
    -2.94
    day
    -2.64
     Day
    -2.63
    Day
    -2.55
     DAY
    -2.52
    DAY
    -2.36
     days
    -2.16
    days
    -2.03
     día
    -2.02
     Days
    -1.99
    POSITIVE LOGITS
    RectangleBorder
    0.63
    +#+#
    0.62
    DoubleQuotes
    0.59
    rungsseite
    0.56
    DebuggerNonUser
    0.51
    toHaveBeen
    0.51
    jstor
    0.50
    SceneManagement
    0.50
    HasAnnotation
    0.50
    toHaveBeenCalled
    0.49
    Activations Density 2.729%

    No Known Activations