© 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. 5587
    Prev
    Next
    INDEX
    Explanations

    periods followed by numbers and underscores, possibly related to versioning or object properties in code

    oai_token-act-pair · gemini-2.0-flash

    parsing code

    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
    ibouti
    -0.60
    matum
    -0.55
    pagestyle
    -0.52
     nahilalakip
    -0.52
     AspNetCore
    -0.50
    itology
    -0.48
    Spoljašnje
    -0.48
     InputDecoration
    -0.47
    ptonshire
    -0.47
    ]='\
    -0.47
    POSITIVE LOGITS
    jsxFileName
    0.57
     الدولى
    0.57
     obstante
    0.54
    لے
    0.53
    createCanvas
    0.52
     mukana
    0.50
     Pov
    0.50
     mukaan
    0.50
     Wikispecies
    0.49
     Vira
    0.49
    Activations Density 0.961%

    No Known Activations