© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13110
    Prev
    Next
    INDEX
    Explanations

    terms related to audio and visual output on electronic devices

    oai_token-act-pair · gemini-2.0-flash

    display

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     архивлан
    -0.91
     CWE
    -0.86
     fallu
    -0.85
    unately
    -0.81
    Atentamente
    -0.80
    setVerticalGroup
    -0.80
    ientôt
    -0.79
     pitié
    -0.77
     quitté
    -0.76
    ratulations
    -0.75
    POSITIVE LOGITS
     tary
    0.67
    o
    0.66
     inves
    0.63
    Clik
    0.60
     PEND
    0.60
     hierogly
    0.60
    blan
    0.59
     nhan
    0.58
     blan
    0.58
    Blan
    0.58
    Activations Density 2.656%

    No Known Activations