© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12556
    Prev
    Next
    INDEX
    Explanations

    math formulas and graph theory, as well as language relating to cults of personality

    oai_token-act-pair · gemini-2.0-flash

    code/math/scientific 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_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     
    -1.06
    ↵
    -1.03
    ,
    -1.01
      
    -0.94
    ↵↵
    -0.91
     (
    -0.88
    .
    -0.87
     I
    -0.87
     a
    -0.84
    <strong>
    -0.83
    POSITIVE LOGITS
    expandindo
    1.93
     Мексичка
    1.91
     للاسماء
    1.86
     فريبيس
    1.80
     CreateTagHelper
    1.79
     يتيمه
    1.71
    LookAnd
    1.68
     propOrder
    1.66
     متعلقه
    1.66
     <=",
    1.65
    Activations Density 3.462%

    No Known Activations