© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5961
    Prev
    Next
    INDEX
    Explanations

    words related to competitive cycling races in Ireland, especially "The Shay Elliott Memorial"

    oai_token-act-pair · gemini-2.0-flash

    Races

    np_max-act-logits · gemini-2.0-flash

    races

    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_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
     كومونز
    -0.73
    WriteTagHelper
    -0.73
    GIVEREF
    -0.72
    Datuak
    -0.72
    ]=>
    -0.69
    MessageOf
    -0.68
    EDEFAULT
    -0.66
     Meksiku
    -0.63
     $__
    -0.62
     فريبيس
    -0.61
    POSITIVE LOGITS
     Race
    0.65
     challenges
    0.62
     races
    0.61
     race
    0.60
     marathon
    0.59
     tri
    0.59
     Ironman
    0.58
     challenge
    0.58
     Iron
    0.58
     tournament
    0.57
    Activations Density 1.480%

    No Known Activations