© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12980
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce a summary or explanation

    oai_token-act-pair · gemini-2.0-flash

    Summarization/Short Explanations

    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
    featureID
    -0.58
     Италијани
    -0.58
    SequentialGroup
    -0.56
    AndroidJUnit
    -0.52
    enumi
    -0.52
     unit
    -0.50
     Administrativna
    -0.50
    kháu
    -0.49
    LabelTagHelper
    -0.48
    navBar
    -0.48
    POSITIVE LOGITS
    NameInMap
    0.71
    CloseOperation
    0.66
     StatefulWidget
    0.62
     ProductService
    0.52
     Majefty
    0.50
     Efq
    0.49
    ^(@)
    0.48
     cappuccio
    0.48
    CGRectMake
    0.48
    gående
    0.47
    Activations Density 0.314%

    No Known Activations