© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10480
    Prev
    Next
    INDEX
    Explanations

    web addresses including "http" or "https"

    oai_token-act-pair · gemini-2.0-flash

    ://

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    لينكات
    -1.00
     للمعارف
    -0.94
     متعلقه
    -0.93
     تضيفلها
    -0.92
     AssemblyTitle
    -0.76
    tagHelperRunner
    -0.75
     الرياضيه
    -0.71
     تانيه
    -0.71
    出版年
    -0.69
    حياتها
    -0.67
    POSITIVE LOGITS
    <eos>
    0.54
     mas
    0.47
     пло
    0.46
    pla
    0.46
     doch
    0.43
     hợp
    0.43
     кле
    0.42
     Pristupljeno
    0.42
    check
    0.41
     UNE
    0.41
    Activations Density 0.605%

    No Known Activations