© 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. 11851
    Prev
    Next
    INDEX
    Explanations

    mentions of racing events and competitions

    oai_token-act-pair · gemini-2.0-flash

    race

    np_max-act · gemini-2.0-flash
    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
     
    -0.84
     $
    -0.69
    FFER
    -0.65
     Geist
    -0.64
     mises
    -0.61
     '
    -0.59
    ا
    -0.59
     prie
    -0.57
     minutes
    -0.57
      
    -0.57
    POSITIVE LOGITS
     bezeichneter
    1.12
    GraphicsUnit
    1.04
    MemoryWarning
    0.98
    #+#
    0.98
    tagHelperRunner
    0.92
     resourceCulture
    0.91
     насељу
    0.89
     defaultstate
    0.88
    TestingModule
    0.87
     виправивши
    0.87
    Activations Density 3.046%

    No Known Activations