© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10945
    Prev
    Next
    INDEX
    Explanations

    negation and the verb "to be."

    oai_token-act-pair · gemini-2.0-flash

    negation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     useCallback
    -0.56
     Италијани
    -0.54
    colgroup
    -0.54
    naux
    -0.51
    adpleegd
    -0.51
    LabelTagHelper
    -0.50
    onViewCreated
    -0.50
    Bunch
    -0.48
    too
    -0.47
     newInstance
    -0.47
    POSITIVE LOGITS
     Efq
    0.63
    ="#"><
    0.60
    Билгалдахарш
    0.60
    AccessorTable
    0.57
     greateſt
    0.57
     deſt
    0.55
     magasiner
    0.55
    Hozzáférés
    0.54
     Inſ
    0.54
     purpoſe
    0.54
    Activations Density 4.895%

    No Known Activations