Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9589
    Prev
    Next
    INDEX
    Explanations

    the phrase "real time" and related context

    oai_token-act-pair · gemini-2.0-flash

    real estate/time

    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
     Real
    -3.11
    Real
    -3.11
     REAL
    -2.84
    REAL
    -2.81
    real
    -2.73
     real
    -2.56
     realism
    -2.05
     realist
    -2.02
     réal
    -1.97
     Reality
    -1.94
    POSITIVE LOGITS
    WindowConstants
    0.57
    addGroup
    0.56
    WaitGroup
    0.56
    iNdEx
    0.54
     BorderRadius
    0.54
    +#+
    0.53
    rógeno
    0.50
     capot
    0.49
    tabak
    0.49
    onAttach
    0.49
    Activations Density 4.108%

    No Known Activations