© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11034
    Prev
    Next
    INDEX
    Explanations

    language related to oil production costs and demand

    oai_token-act-pair · gemini-2.0-flash

    global economics/trade

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    webElementXpaths
    -0.76
     JpaRepository
    -0.75
    tagHelperRunner
    -0.74
    StoryboardSegue
    -0.71
    GEBURTSDATUM
    -0.68
    ")){
    -0.65
    Diweddarwch
    -0.63
    CloseOperation
    -0.63
    ReusableCell
    -0.61
    BagLayout
    -0.60
    POSITIVE LOGITS
    ⓧ
    0.61
    دانشنامهٔ
    0.56
     currencies
    0.48
     populaires
    0.48
    setGravity
    0.48
    openzeppelin
    0.48
    isan
    0.47
    Pars
    0.47
     éner
    0.47
    cosx
    0.46
    Activations Density 7.846%

    No Known Activations