© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12409
    Prev
    Next
    INDEX
    Explanations

    brand names for clothing and entertainment

    oai_token-act-pair · gemini-2.0-flash

    Armour

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     lanjut
    -0.57
     løpet
    -0.51
    Bias
    -0.48
    akaian
    -0.48
     littéraire
    -0.47
     grecque
    -0.47
     Provinces
    -0.47
    endpush
    -0.47
     acela
    -0.47
     yolks
    -0.46
    POSITIVE LOGITS
     通販
    0.94
    ⓧ
    0.74
    interopRequire
    0.66
     ویکی‌پدیای
    0.66
    PMailer
    0.65
     transfieras
    0.61
    下载附件
    0.60
     AssemblyCompany
    0.60
    openzeppelin
    0.60
     صوتيه
    0.59
    Activations Density 0.493%

    No Known Activations