© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14247
    Prev
    Next
    INDEX
    Explanations

    the word "protocol"

    oai_token-act-pair · gemini-2.0-flash

    protocol

    np_max-act · gemini-2.0-flash

    protocol

    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
    mybatisplus
    -1.07
     calendriers
    -0.85
    ruptedException
    -0.82
    openzeppelin
    -0.75
    TargetException
    -0.75
    colnshire
    -0.73
    Abitanti
    -0.71
     ComVisible
    -0.71
    omitempty
    -0.70
    Население
    -0.70
    POSITIVE LOGITS
     oseb
    0.67
    cit
    0.62
     umane
    0.60
     DeV
    0.60
     compétence
    0.59
     mijne
    0.58
     superiori
    0.58
     esperienze
    0.57
     särsk
    0.57
    kol
    0.57
    Activations Density 1.372%

    No Known Activations