© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2089
    Prev
    Next
    INDEX
    Explanations

    descriptions of an investigation, hunt, or difficult journey

    oai_token-act-pair · gemini-2.0-flash

    pursuit

    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
    iços
    -0.57
     szóci
    -0.51
    cetamol
    -0.50
    الحياه
    -0.49
    amilya
    -0.47
     cathédrale
    -0.47
    円
    -0.45
     jahr
    -0.44
    lamabad
    -0.44
    pleaños
    -0.44
    POSITIVE LOGITS
    Lähteet
    0.94
     HasFactory
    0.67
     Lightboxes
    0.64
     CreateTagHelper
    0.62
    Искәрмәләр
    0.60
    Hozzáférés
    0.59
    atora
    0.57
    Còn
    0.54
     ErrIntOverflow
    0.54
    Empereur
    0.53
    Activations Density 1.260%

    No Known Activations