© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12602
    Prev
    Next
    INDEX
    Explanations

    scientific or mathematical jargon

    oai_token-act-pair · gemini-2.0-flash

    physics and math proofs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     متعلقه
    -0.99
     <=",
    -0.94
     kasarigan
    -0.87
     صوتيه
    -0.82
     المعيارى
    -0.77
    DoubleQuotes
    -0.74
     <>",
    -0.74
     ModelExpression
    -0.73
    RegressionTest
    -0.72
    ⓧ
    -0.72
    POSITIVE LOGITS
    noStroke
    0.59
    apunov
    0.58
     past
    0.55
    ãng
    0.52
    GetKeyDown
    0.51
    дыду
    0.51
    zit
    0.48
    enservice
    0.48
     hotel
    0.47
    ämmer
    0.47
    Activations Density 5.235%

    No Known Activations