© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3698
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to information and communication

    oai_token-act-pair · gemini-2.0-flash

    Sharing information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     modernes
    -0.51
    OptionsMenu
    -0.47
     Lexikon
    -0.47
     tissus
    -0.46
     độc
    -0.44
     judiciales
    -0.42
    Timer
    -0.41
     руки
    -0.41
     yür
    -0.41
    針對
    -0.40
    POSITIVE LOGITS
    :✨
    0.78
     information
    0.74
    WebVitals
    0.72
    gathered
    0.70
     <=",
    0.69
     info
    0.68
    Informa
    0.65
    information
    0.65
    Hentet
    0.64
     nahilalakip
    0.64
    Activations Density 1.884%

    No Known Activations