© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12588
    Prev
    Next
    INDEX
    Explanations

    words related to computing code as well as abstract concepts in physics and mathematics

    oai_token-act-pair · gemini-2.0-flash

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     đãi
    -0.49
    NERS
    -0.46
     externi
    -0.45
    èves
    -0.44
    PORARY
    -0.42
     top
    -0.42
    الحياه
    -0.41
    ègre
    -0.40
    ners
    -0.40
    ipedi
    -0.40
    POSITIVE LOGITS
    numerusform
    0.88
    IntoConstraints
    0.69
    titleMargin
    0.65
     raiſ
    0.63
    tagHelperRunner
    0.63
    bootstrapcdn
    0.61
    InsertCommand
    0.60
     Económica
    0.60
     Jurí
    0.60
     offside
    0.58
    Activations Density 0.513%

    No Known Activations