© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8456
    Prev
    Next
    INDEX
    Explanations

    the French phrase "quelqu'un" (someone) and related words and context

    oai_token-act-pair · gemini-2.0-flash

    qu

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    RectangleBorder
    -0.58
     autorytatywna
    -0.58
    AutoScaleMode
    -0.57
     ―――――
    -0.57
     thoſe
    -0.57
    AndEndTag
    -0.57
    oient
    -0.55
    voirs
    -0.54
    protoc
    -0.54
     ――――
    -0.54
    POSITIVE LOGITS
    something
    1.77
     something
    1.77
    Something
    1.69
     Something
    1.56
     SOMETHING
    1.41
     somethin
    1.36
    someone
    1.34
     someone
    1.31
    Someone
    1.30
     somebody
    1.29
    Activations Density 0.287%

    No Known Activations