© 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. 5434
    Prev
    Next
    INDEX
    Explanations

    mentions of the year 1900s

    oai_token-act-pair · gemini-2.0-flash

    1

    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
     pleaſure
    -0.70
     purpoſe
    -0.68
    jspx
    -0.63
     ſtate
    -0.60
     Majefty
    -0.60
     houſe
    -0.59
     neceff
    -0.58
     عشر
    -0.57
    neſs
    -0.57
     jir
    -0.56
    POSITIVE LOGITS
    9
    0.85
     مشين
    0.69
     mid
    0.57
    endphp
    0.56
    ９
    0.56
    ೯
    0.56
     WaitForSeconds
    0.48
    existsSync
    0.48
     propOrder
    0.48
    mug
    0.47
    Activations Density 1.380%

    No Known Activations