© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15820
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and expressions, especially those involving multiplication, division, and exponents, and related figures and tables of data

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    setArguments
    -0.60
     salari
    -0.57
    фіка
    -0.54
    Vorlage
    -0.54
     candidats
    -0.52
    ensee
    -0.52
    cett
    -0.52
    jima
    -0.52
     are
    -0.51
    chka
    -0.50
    POSITIVE LOGITS
    writeFieldEnd
    0.67
    StoryboardSegue
    0.65
    oneofs
    0.59
    ❹
    0.56
    sizeCache
    0.56
    parsedMessage
    0.56
    UserScript
    0.55
    windowFixed
    0.55
    xase
    0.55
    oa̍t
    0.55
    Activations Density 9.029%

    No Known Activations