© 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. 13917
    Prev
    Next
    INDEX
    Explanations

    baseball-related terms, especially information about baseball players

    oai_token-act-pair · gemini-2.0-flash

    baseball

    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
     EconPapers
    -0.56
    ResponseWriter
    -0.52
     protoimpl
    -0.50
    StackNavigator
    -0.50
     lccn
    -0.49
     unknownFields
    -0.49
     podjela
    -0.48
     ModelAndView
    -0.48
     rurales
    -0.47
     MongoClient
    -0.47
    POSITIVE LOGITS
     out
    0.52
     thermoc
    0.51
    허
    0.50
    OF
    0.50
     OF
    0.49
    reli
    0.48
     jScrollPane
    0.48
    rof
    0.48
     hashCode
    0.47
    catching
    0.47
    Activations Density 0.692%

    No Known Activations