© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10095
    Prev
    Next
    INDEX
    Explanations

    words and phrases that express location or political conflict or retreat to a safe place

    oai_token-act-pair · gemini-2.0-flash

    base or respite location

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    WaitGroup
    -0.79
    isContained
    -0.64
     Wikimedijinoj
    -0.56
    SizeF
    -0.56
    ResponseWriter
    -0.55
    nextProps
    -0.54
     føl
    -0.54
    DataBind
    -0.53
     InputDecoration
    -0.53
     connais
    -0.53
    POSITIVE LOGITS
     kasarigan
    0.71
     imageNamed
    0.59
    σίας
    0.53
    toMatch
    0.52
    uttavia
    0.52
    fusc
    0.52
     nat
    0.51
    inhua
    0.51
    WebElementEntity
    0.50
    ecution
    0.50
    Activations Density 2.382%

    No Known Activations