© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14575
    Prev
    Next
    INDEX
    Explanations

    words related to sports tournaments and athletic competitions

    oai_token-act-pair · gemini-2.0-flash

    sports tournaments

    np_max-act · gemini-2.0-flash

    conference

    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_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
    transQ
    -0.56
    stalt
    -0.55
    Étymologie
    -0.54
     tjen
    -0.52
     åt
    -0.51
     tromper
    -0.50
     CURLOPT
    -0.50
     célèbres
    -0.50
    hoeddwyd
    -0.50
     mergeFrom
    -0.50
    POSITIVE LOGITS
     Freshman
    0.60
     freshman
    0.57
    Sophomore
    0.56
     Sophomore
    0.56
     dras
    0.56
     
    0.55
    itoire
    0.54
     freshmen
    0.53
    curricular
    0.52
    concel
    0.52
    Activations Density 1.034%

    No Known Activations