© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15036
    Prev
    Next
    INDEX
    Explanations

    context about weather and dates

    oai_token-act-pair · gemini-2.0-flash

    Outdoor activities and travel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     AssemblyCompany
    -0.47
    //
    -0.44
    허
    -0.42
    lavi
    -0.40
    his
    -0.40
    u
    -0.40
    awaiter
    -0.39
    setState
    -0.39
    lige
    -0.39
     annonces
    -0.39
    POSITIVE LOGITS
     it
    0.90
     חיצוניים
    0.74
     noDo
    0.73
     оригіналу
    0.70
     Efq
    0.69
     preſent
    0.65
     autorytatywna
    0.65
    olites
    0.64
     poffe
    0.64
     anhyd
    0.63
    Activations Density 7.470%

    No Known Activations