© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4439
    Prev
    Next
    INDEX
    Explanations

    names, social media mentions, and discussions about social justice issues

    oai_token-act-pair · gemini-2.0-flash

    Diverse, informal writing snippets

    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
    تقاوى
    -0.63
    hilangan
    -0.56
    listdir
    -0.54
    TabStop
    -0.54
     MainAxisSize
    -0.52
    @
    -0.52
     rospy
    -0.52
    UserScript
    -0.52
    онер
    -0.52
    بوابة
    -0.50
    POSITIVE LOGITS
     AssemblyProduct
    0.64
     kasarigan
    0.63
     חיצוניים
    0.52
     Numerade
    0.47
    ÊNCIAS
    0.47
    étaire
    0.46
    ElementException
    0.46
     lunar
    0.46
    itness
    0.45
     Matériau
    0.45
    Activations Density 0.653%

    No Known Activations