© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9874
    Prev
    Next
    INDEX
    Explanations

    the word "inclusion."

    oai_token-act-pair · gemini-2.0-flash

    inclusion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ↵↵
    -0.57
     tendenza
    -0.54
     individuelles
    -0.53
     menga
    -0.53
     distribuzione
    -0.51
     silicona
    -0.50
     konkrete
    -0.50
     vivimos
    -0.50
    صحاب
    -0.50
     konkret
    -0.50
    POSITIVE LOGITS
    PerformLayout
    0.91
    sidemargin
    0.85
    SharedCtor
    0.85
     ComVisible
    0.84
    SqlParameter
    0.80
    mybatisplus
    0.78
     ujednoznacz
    0.77
    хьтан
    0.76
    '));
    0.75
    ValueStyle
    0.74
    Activations Density 1.974%

    No Known Activations