© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6637
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to local community, activities, and interactions, especially those involving youth.

    oai_token-act-pair · gemini-2.0-flash

    sports

    np_max-act-logits · gemini-2.0-flash

    youth recreation

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     nakalista
    -0.80
    tvguidetime
    -0.78
    AxisAlignment
    -0.72
    uxxxx
    -0.71
    AutoScale
    -0.70
    RectangleBorder
    -0.70
    EndContext
    -0.69
    SuppressMessage
    -0.65
     localObject
    -0.65
    AccessorTable
    -0.62
    POSITIVE LOGITS
     sports
    0.81
     sport
    0.74
     basketball
    0.73
     Sports
    0.68
     baseball
    0.66
     tennis
    0.65
     Sport
    0.65
     softball
    0.64
    Sports
    0.64
     sporting
    0.63
    Activations Density 1.116%

    No Known Activations