© 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. 131
    Prev
    Next
    INDEX
    Explanations

    terminology and concepts related to digital computing, especially binary digits and data processing.

    oai_token-act-pair · gemini-2.0-flash

    Binary digits

    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
    kuuta
    -0.57
     soát
    -0.56
    NamedQuery
    -0.54
     vyk
    -0.54
    quias
    -0.54
     Schlag
    -0.53
    WebVitals
    -0.52
    المناصب
    -0.50
     recientes
    -0.49
    balleur
    -0.49
    POSITIVE LOGITS
     AppComponent
    0.59
     vastaan
    0.56
     palsu
    0.49
     atve
    0.48
    mphony
    0.47
    ricultural
    0.46
    SwitchCompat
    0.45
     vendre
    0.45
     defaultstate
    0.44
    경
    0.44
    Activations Density 3.161%

    No Known Activations