© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8527
    Prev
    Next
    INDEX
    Explanations

    mentions of ancient times and/or quantum physics

    oai_token-act-pair · gemini-2.0-flash

    ancient

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     miracle
    -0.69
     civilisation
    -0.69
     personalise
    -0.69
     miracles
    -0.63
     itſelf
    -0.61
    Yourself
    -0.60
     mankind
    -0.60
     realisation
    -0.60
     thyself
    -0.58
     splendour
    -0.58
    POSITIVE LOGITS
    =*/
    0.71
    \}\\
    0.67
     Процитовано
    0.64
    »։
    0.64
     OnInit
    0.63
     led
    0.62
    embolso
    0.61
     further
    0.61
    ValueStyle
    0.60
     only
    0.60
    Activations Density 2.461%

    No Known Activations