© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2977
    Prev
    Next
    INDEX
    Explanations

    words related to hobbies, activities, clubs, and classes.

    oai_token-act-pair · gemini-2.0-flash

    sports

    np_max-act · gemini-2.0-flash

    sports

    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_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     sports
    -2.20
    Sports
    -2.06
     sport
    -2.06
     Sports
    -2.05
    sports
    -1.92
    sport
    -1.88
     Sport
    -1.88
    Sport
    -1.84
     SPORTS
    -1.70
     SPORT
    -1.66
    POSITIVE LOGITS
    ruptedException
    0.55
     boletos
    0.54
     <<=
    0.52
    δί
    0.52
     nakalista
    0.51
    Filmografia
    0.48
    onOptions
    0.47
     intensification
    0.46
     resourceCulture
    0.46
    yscale
    0.46
    Activations Density 5.902%

    No Known Activations