© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6346
    Prev
    Next
    INDEX
    Explanations

    mentions of the "Green" political party or the color green

    oai_token-act-pair · gemini-2.0-flash

    green

    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
    LookAnd
    -0.85
    IndentedString
    -0.75
    oa̍t
    -0.66
    Jeografia
    -0.66
    StructEnd
    -0.66
    ItemBackground
    -0.66
    featureID
    -0.65
    NameInMap
    -0.65
    Lähteet
    -0.64
    tagHelperRunner
    -0.62
    POSITIVE LOGITS
     sumpay
    0.52
    sprach
    0.51
    trecht
    0.50
     thumb
    0.49
    ignac
    0.48
    บาล
    0.47
    WidgetItem
    0.47
     inquest
    0.46
    SPARENT
    0.45
    はじめに
    0.45
    Activations Density 0.678%

    No Known Activations