© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13456
    Prev
    Next
    INDEX
    Explanations

    political discourse (specifically related to the U.S. Congress)

    oai_token-act-pair · gemini-2.0-flash

    blocking, overturning

    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
    ReusableCell
    -0.75
     springfox
    -0.65
    eleste
    -0.65
     BoxDecoration
    -0.62
    AddTagHelper
    -0.60
     ModelExpression
    -0.56
     RoutedEventArgs
    -0.56
    DebuggerNonUser
    -0.54
    łucha
    -0.54
    mybatisplus
    -0.53
    POSITIVE LOGITS
     overturned
    0.70
    GOTREF
    0.66
     blocked
    0.63
     overturn
    0.59
     blocking
    0.57
     veto
    0.56
     nul
    0.53
     fili
    0.53
     Blocking
    0.53
     block
    0.53
    Activations Density 2.560%

    No Known Activations