© 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. 4455
    Prev
    Next
    INDEX
    Explanations

    the word "attention," and words associated with giving, receiving, or requiring attention

    oai_token-act-pair · gemini-2.0-flash

    attention

    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
     nahilalakip
    -0.78
    ]")]
    -0.73
    principalColumn
    -0.68
    astéroïdes
    -0.68
     MessageBoxIcon
    -0.67
    ViewImports
    -0.67
    yntaxException
    -0.66
    StoryboardSegue
    -0.65
     useRouter
    -0.64
     Exacts
    -0.63
    POSITIVE LOGITS
     Starr
    0.48
     саме
    0.45
     focused
    0.44
     tertarik
    0.43
     si
    0.43
     terakhir
    0.42
     transfieras
    0.42
     peccato
    0.41
     dağı
    0.41
    box
    0.41
    Activations Density 1.973%

    No Known Activations