© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14855
    Prev
    Next
    INDEX
    Explanations

    code and city/location names

    oai_token-act-pair · gemini-2.0-flash

    body

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ChildScrollView
    -0.67
     MainAxisSize
    -0.63
    endphp
    -0.63
    ✨:
    -0.62
    tráfico
    -0.59
    etheless
    -0.58
    glises
    -0.57
    日閲覧
    -0.56
     venons
    -0.55
     didReceive
    -0.55
    POSITIVE LOGITS
    τρα
    0.59
    ("")){
    0.57
     Hummel
    0.57
     aloud
    0.55
     Magi
    0.52
     Mathis
    0.51
     Commanders
    0.51
    mand
    0.50
     lenta
    0.50
     loudly
    0.49
    Activations Density 1.703%

    No Known Activations