© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16023
    Prev
    Next
    INDEX
    Explanations

    the string "tra"

    oai_token-act-pair · gemini-2.0-flash

    tra

    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
     
    -1.17
    g
    -1.04
    ,
    -0.98
    .
    -0.93
     /
    -0.93
    /
    -0.91
    s
    -0.90
     (
    -0.87
     or
    -0.87
    ing
    -0.85
    POSITIVE LOGITS
     Efq
    1.99
     myſelf
    1.98
    setVerticalGroup
    1.77
     itſelf
    1.70
     Monfieur
    1.66
     ―――――
    1.61
     ſeveral
    1.60
    RenderAtEndOf
    1.60
    RectangleBorder
    1.60
     дописавши
    1.60
    Activations Density 2.016%

    No Known Activations