© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12698
    Prev
    Next
    INDEX
    Explanations

    capitalized proper nouns/names

    oai_token-act-pair · gemini-2.0-flash

    legal cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    interopRequire
    -0.62
     autorytatywna
    -0.62
    igshid
    -0.57
    invokeLater
    -0.51
    chell
    -0.49
    uesday
    -0.49
    IsPostBack
    -0.48
     Wayback
    -0.47
     estimés
    -0.47
    Източници
    -0.47
    POSITIVE LOGITS
     мәкал
    0.65
    IntoConstraints
    0.61
    iconque
    0.56
    URUS
    0.52
    prepareStatement
    0.51
     himself
    0.49
    enderror
    0.49
     invokingState
    0.49
    lamabad
    0.49
     Himself
    0.48
    Activations Density 1.771%

    No Known Activations