© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 633
    Prev
    Next
    INDEX
    Explanations

    phrases expressing political opinions and social commentary

    oai_token-act-pair · gemini-2.0-flash

    modern

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     виправивши
    -0.58
     Welt
    -0.55
     העולם
    -0.52
    Society
    -0.51
     Azz
    -0.49
     domin
    -0.48
    рачи
    -0.48
    ChildScrollView
    -0.47
    saus
    -0.47
     SOCIETY
    -0.46
    POSITIVE LOGITS
    EndContext
    0.77
    kloped
    0.77
    ContentAsync
    0.74
    httphttps
    0.62
    principalColumn
    0.60
    contentLoaded
    0.60
     nahilalakip
    0.60
    principalTable
    0.59
     transfieras
    0.57
     pinulongan
    0.57
    Activations Density 10.954%

    No Known Activations