© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9324
    Prev
    Next
    INDEX
    Explanations

    college and professional sports teams

    oai_token-act-pair · gemini-2.0-flash

    sports-related terms

    np_token-act-pair-logits · gpt-4o-mini

    sports teams and players

    np_max-act-logits · gemini-2.0-flash

    s

    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_21/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.21.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
     bride
    -0.52
    :✨
    -0.51
    Mojo
    -0.48
    ########.
    -0.46
     Saxons
    -0.46
    mule
    -0.44
    AppContext
    -0.44
     Brah
    -0.44
     migraine
    -0.43
     Spine
    -0.42
    POSITIVE LOGITS
     ice
    0.98
     hockey
    0.84
     Ice
    0.82
     soccer
    0.76
     volleyball
    0.75
     basketball
    0.75
    Ice
    0.74
    volley
    0.73
     rugby
    0.73
     cricket
    0.70
    Activations Density 1.032%

    No Known Activations