© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7019
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with precise measurements

    oai_token-act-pair · gemini-2.0-flash

    accuracy and precision

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     referenties
    -0.50
     defaultstate
    -0.48
    ۇ
    -0.46
    LineColor
    -0.43
    outState
    -0.42
     Kante
    -0.42
     kia
    -0.42
     RemoteException
    -0.41
    HasKey
    -0.41
     lobo
    -0.41
    POSITIVE LOGITS
     accuracy
    1.37
     precision
    1.22
     Accuracy
    1.16
    accuracy
    1.12
     accurate
    1.07
    precision
    1.04
    Accuracy
    1.02
     Precision
    1.00
    accurate
    0.99
     ACCUR
    0.96
    Activations Density 1.989%

    No Known Activations