© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5887
    Prev
    Next
    INDEX
    Explanations

    the word "display" or plural of "display" in a technical context

    oai_token-act-pair · gemini-2.0-flash

    display

    np_max-act · gemini-2.0-flash

    display

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     szabad
    -0.76
     képes
    -0.75
     oreilles
    -0.71
     mør
    -0.71
     guerres
    -0.69
     kereszt
    -0.68
     scienza
    -0.67
     Parigi
    -0.66
     fejles
    -0.65
     különböz
    -0.65
    POSITIVE LOGITS
    ChildScrollView
    1.04
     mxArray
    1.02
    MemoryWarning
    1.02
    GEBURTSDATUM
    1.02
    sidemargin
    1.01
     CURIAM
    1.00
    tvguidetime
    0.98
    الحياه
    0.98
    WriteBarrier
    0.97
    PhysRevD
    0.96
    Activations Density 3.844%

    No Known Activations