© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10982
    Prev
    Next
    INDEX
    Explanations

    language relating to sports team dynamics, injuries, and player availability

    oai_token-act-pair · gemini-2.0-flash

    Sports training

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    SceneManagement
    -0.58
     Trainings
    -0.57
     Training
    -0.52
     Sol
    -0.52
     TRAINING
    -0.50
     training
    -0.49
     la
    -0.48
    bouncycastle
    -0.48
    ناية
    -0.48
    انيف
    -0.48
    POSITIVE LOGITS
     EconPapers
    0.78
    WillAppear
    0.66
    ArgsConstructor
    0.58
     defaultstate
    0.57
    Portály
    0.56
     चीज़ों
    0.53
    Toponymie
    0.53
    EndContext
    0.52
    hyrchwyd
    0.51
    JNIEnv
    0.51
    Activations Density 1.835%

    No Known Activations