© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11681
    Prev
    Next
    INDEX
    Explanations

    words and phrases suggesting relationships

    oai_token-act-pair · gemini-2.0-flash

    committed relationship

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     intptr
    -0.73
    OGND
    -0.67
    GOTREF
    -0.59
    最快更新
    -0.57
    contentLoaded
    -0.57
    StoryboardSegue
    -0.54
     nahilalakip
    -0.52
    Obrázky
    -0.52
    MLLoader
    -0.50
    رشف
    -0.48
    POSITIVE LOGITS
     committed
    0.91
     Committed
    0.75
    committed
    0.74
     relationship
    0.73
     relationships
    0.69
     civil
    0.68
     commit
    0.66
    Committed
    0.66
    long
    0.65
     COMMIT
    0.65
    Activations Density 3.063%

    No Known Activations