© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7031
    Prev
    Next
    INDEX
    Explanations

    words related to sports races, particularly the specific race being discussed in the document

    oai_token-act-pair · gemini-2.0-flash

    races and outdoor activities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     running
    -1.01
     ran
    -0.97
     Running
    -0.96
     RUNNING
    -0.94
    Running
    -0.91
    runs
    -0.90
     runs
    -0.90
    running
    -0.90
     run
    -0.88
     Runs
    -0.85
    POSITIVE LOGITS
     saites
    0.56
    SequentialGroup
    0.55
    agung
    0.49
    protoimpl
    0.49
    கம்
    0.48
    Ừ
    0.48
    TextFormField
    0.46
     agricoles
    0.46
    lielmo
    0.45
     puissiez
    0.43
    Activations Density 1.239%

    No Known Activations