© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3834
    Prev
    Next
    INDEX
    Explanations

    complex syntax separating ideas, or logical/literary constructions.

    oai_token-act-pair · gemini-2.0-flash

    web page text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    fluence
    -0.46
     setText
    -0.45
    trise
    -0.44
     Fund
    -0.42
    ':[
    -0.40
     useContext
    -0.40
     Tr
    -0.40
    ]=-
    -0.40
    mug
    -0.38
    [__
    -0.38
    POSITIVE LOGITS
     ſtand
    0.71
     pleaſure
    0.68
    HasForeignKey
    0.67
    DeleteBehavior
    0.67
    initComponents
    0.65
     Wiktionnaire
    0.63
     ſhould
    0.63
     ſtate
    0.60
     quæ
    0.60
     reaſon
    0.59
    Activations Density 2.791%

    No Known Activations