© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7583
    Prev
    Next
    INDEX
    Explanations

    descriptions of wrestling matches and payments

    oai_token-act-pair · gemini-2.0-flash

    Wrestling

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    providedIn
    -0.73
    NameInMap
    -0.68
    MENAFN
    -0.63
    DotNetBar
    -0.63
    клопе
    -0.63
    setVerticalGroup
    -0.61
     CURIAM
    -0.61
     vectorielle
    -0.57
     atteinte
    -0.57
    }}=$
    -0.57
    POSITIVE LOGITS
     WWE
    0.56
     Wrestling
    0.54
     tag
    0.52
     wrestling
    0.51
    DDT
    0.50
     ring
    0.50
     wrestlers
    0.50
     دب
    0.49
    Wrestling
    0.48
    WWE
    0.48
    Activations Density 0.348%

    No Known Activations