© 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. 5314
    Prev
    Next
    INDEX
    Explanations

    words commonly used when talking about someone's performance

    oai_token-act-pair · gemini-2.0-flash

    Sports/Player performance

    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
    findpost
    -0.68
     kasarigan
    -0.62
    ISupport
    -0.59
     }}"></
    -0.57
    sieu
    -0.57
     مرئيه
    -0.56
    Ragnar
    -0.56
    ReusableCell
    -0.56
     bodyParser
    -0.56
     NSCoder
    -0.56
    POSITIVE LOGITS
     momentum
    0.59
    hot
    0.56
     hot
    0.52
    verwijspagina
    0.51
     trending
    0.50
    TintMode
    0.50
     form
    0.48
     well
    0.47
    Geografía
    0.47
     good
    0.46
    Activations Density 0.559%

    No Known Activations