© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7719
    Prev
    Next
    INDEX
    Explanations

    words ending in "ations", as in "discontinuations" or "confrontations", often within the context of studies or medical texts .

    oai_token-act-pair · gemini-2.0-flash

    ations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ations
    -2.11
    ation
    -2.02
    ATION
    -1.70
    ATIONS
    -1.55
    ación
    -1.16
    ationen
    -1.14
    aciones
    -1.05
    azioni
    -1.05
    azione
    -1.02
    isations
    -1.00
    POSITIVE LOGITS
    mybatisplus
    0.70
     [*]
    0.64
    tvguidetime
    0.59
    BeginContext
    0.59
    HasForeignKey
    0.55
    uxxxx
    0.55
    Mockito
    0.54
     cytometry
    0.54
    MeasureSpec
    0.51
    MethodManager
    0.51
    Activations Density 1.379%

    No Known Activations