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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9725
    Prev
    Next
    INDEX
    Explanations

    topics related to being elderly and old, especially age thresholds

    oai_token-act-pair · gemini-2.0-flash

    over

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    typeorm
    -0.54
    Xna
    -0.53
    公
    -0.49
    личие
    -0.43
    kyard
    -0.43
    нского
    -0.42
    ked
    -0.42
     EClass
    -0.42
    bine
    -0.40
     xếp
    -0.39
    POSITIVE LOGITS
     over
    2.56
    over
    2.02
     Over
    1.91
    Over
    1.91
     OVER
    1.84
     över
    1.77
    OVER
    1.66
     über
    1.45
    overs
    1.41
     над
    1.29
    Activations Density 2.777%

    No Known Activations