© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14254
    Prev
    Next
    INDEX
    Explanations

    php code iterating through and accessing array key/value pairs

    oai_token-act-pair · gemini-2.0-flash

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     daß
    -0.98
    DockStyle
    -0.84
    رشف
    -0.80
     läßt
    -0.77
    tagHelperRunner
    -0.75
     (;;)
    -0.74
     חיצוניים
    -0.73
     vícti
    -0.73
    AnchorStyles
    -0.72
     müßte
    -0.69
    POSITIVE LOGITS
    createNewFile
    0.61
    Lastly
    0.56
    gorm
    0.54
     Lastly
    0.53
     lastly
    0.52
     основании
    0.52
     deem
    0.52
     particolar
    0.51
    Utili
    0.50
     şekilde
    0.50
    Activations Density 0.716%

    No Known Activations