© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11373
    Prev
    Next
    INDEX
    Explanations

    emotionally charged narrative phrases and legal concepts

    oai_token-act-pair · gemini-2.0-flash

    Relationships and political discourse

    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
    AndroidJUnit
    -0.71
     VizieR
    -0.70
    +#+#
    -0.69
    verwijspagina
    -0.66
    spesies
    -0.63
    BagConstraints
    -0.63
    VersionUID
    -0.62
    styleable
    -0.62
    NameInMap
    -0.62
    TextWatcher
    -0.60
    POSITIVE LOGITS
     drap
    0.42
    oxidase
    0.42
    zco
    0.41
    codiles
    0.40
     للاسماء
    0.39
     Appeal
    0.39
    gania
    0.39
    äume
    0.38
    titions
    0.38
     Mechan
    0.38
    Activations Density 0.716%

    No Known Activations