© 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. 6928
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with sports matches or wrestlers

    oai_token-act-pair · gemini-2.0-flash

    Names and titles

    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
     she
    -2.28
     herself
    -2.16
     her
    -1.95
     그녀
    -1.84
    herself
    -1.80
     girl
    -1.75
     woman
    -1.70
     hers
    -1.69
    she
    -1.68
     shes
    -1.66
    POSITIVE LOGITS
    DatabaseError
    0.35
     localObject
    0.35
    icolo
    0.34
    父子
    0.33
    udra
    0.33
    ueltos
    0.32
    onnais
    0.32
    xtick
    0.31
     thiệu
    0.31
     verlo
    0.29
    Activations Density 35.374%

    No Known Activations