© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11694
    Prev
    Next
    INDEX
    Explanations

    descriptive words indicating strong opinions or preferences

    oai_token-act-pair · gemini-2.0-flash

    Enthusiastic fans

    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
    martre
    -0.57
    Попис
    -0.56
    prepareStatement
    -0.49
    MemoryWarning
    -0.49
    figer
    -0.48
    DllImport
    -0.47
    batore
    -0.46
    ливо
    -0.46
     يتيمه
    -0.46
    FXMLLoader
    -0.46
    POSITIVE LOGITS
     فريبيس
    0.66
     die
    0.56
     buff
    0.56
     passing
    0.56
    CodeDom
    0.54
     Chaucer
    0.53
     devoted
    0.52
     utafitiHapana
    0.52
    Besch
    0.51
     committed
    0.50
    Activations Density 1.080%

    No Known Activations