© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10898
    Prev
    Next
    INDEX
    Explanations

    HTML table row and table data tags, along with image tags inside a href tags

    oai_token-act-pair · gemini-2.0-flash

    HTML tables

    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
     ruote
    -0.51
     quæ
    -0.50
     raiſ
    -0.47
     Cuckoo
    -0.47
     CHAPITRE
    -0.47
     universel
    -0.45
     électro
    -0.45
     eccl
    -0.44
     cdr
    -0.44
    响
    -0.44
    POSITIVE LOGITS
     nahilalakip
    0.91
    ंदीखरीदारी
    0.85
     CreateTagHelper
    0.79
    NewUrlParser
    0.73
    tagHelperRunner
    0.71
    WithMany
    0.71
    ThroughAttribute
    0.70
     transfieras
    0.69
    AnchorStyles
    0.68
    WireFormatLite
    0.68
    Activations Density 0.258%

    No Known Activations