© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3707
    Prev
    Next
    INDEX
    Explanations

    words related to sports, especially football (or perhaps soccer) and their jargon

    oai_token-act-pair · gemini-2.0-flash

    sports and football

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     jelent
    -0.53
    tagHelperRunner
    -0.52
    msgTypes
    -0.52
    NgModule
    -0.49
    INCREF
    -0.48
     combineReducers
    -0.47
     transfieras
    -0.46
     صوتيه
    -0.46
    viewtopic
    -0.44
     appunt
    -0.43
    POSITIVE LOGITS
     resourceCulture
    0.73
    
    0.62
     通販
    0.61
     مشين
    0.59
    endphp
    0.57
    <?
    0.56
     CrossRef
    0.53
     GENERATED
    0.52
    ElementException
    0.52
    exitRule
    0.51
    Activations Density 0.387%

    No Known Activations