© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13259
    Prev
    Next
    INDEX
    Explanations

    references to sports teams, baseball and football statistics, and common words used in sports reporting.

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    AddTagHelper
    -0.64
     Allociné
    -0.58
     ComVisible
    -0.56
    complexContent
    -0.55
    HasForeignKey
    -0.54
    lesi
    -0.54
     ProtoMessage
    -0.54
    itability
    -0.54
    Personendaten
    -0.54
    contentLoaded
    -0.53
    POSITIVE LOGITS
     quæ
    0.48
    обеди
    0.47
     actionMode
    0.47
    Football
    0.47
     reaſon
    0.45
     Football
    0.45
     Zusch
    0.45
     competitivos
    0.45
     plastica
    0.45
     Cyl
    0.43
    Activations Density 2.542%

    No Known Activations