© 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. 9628
    Prev
    Next
    INDEX
    Explanations

    words related to a wide range of different parameters, descriptions, or possible options

    oai_token-act-pair · gemini-2.0-flash

    variety

    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
     visualiser
    -0.68
    xically
    -0.66
     recognises
    -0.64
     />\
    -0.62
     ویکی‌پدیا
    -0.62
     ostensibly
    -0.61
     arguably
    -0.61
     recognising
    -0.57
     recognise
    -0.57
     variously
    -0.57
    POSITIVE LOGITS
    favorable
    0.60
    rungsseite
    0.57
     eseguire
    0.56
     harbors
    0.56
    Diweddarwch
    0.56
     harbor
    0.55
    vece
    0.55
     specialmente
    0.54
     favorable
    0.54
    quois
    0.54
    Activations Density 1.159%

    No Known Activations