© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11094
    Prev
    Next
    INDEX
    Explanations

    a list of networked electronic devices, especially when preceded by "a", "an", or "the"

    oai_token-act-pair · gemini-2.0-flash

    security cameras and video

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    QPalette
    -0.58
     mă
    -0.54
    httphttps
    -0.54
     vettoriale
    -0.53
    abestanden
    -0.51
    GeneratedValue
    -0.51
    WillAppear
    -0.50
     OMITBAD
    -0.49
     defaultstate
    -0.49
    ValueStyle
    -0.47
    POSITIVE LOGITS
     advanced
    0.60
    }`}>
    0.58
     Recording
    0.56
    商品説明
    0.56
    Recording
    0.55
     recording
    0.55
     DVR
    0.55
     attendance
    0.54
    $")
    0.54
     camera
    0.53
    Activations Density 1.935%

    No Known Activations