© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 498
    Prev
    Next
    INDEX
    Explanations

    terms related to Japanese history and institutions, along with company names

    oai_token-act-pair · gemini-2.0-flash

    Japanese articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    الإنجليزية
    -0.59
     >=",
    -0.57
    currentThread
    -0.53
     виправивши
    -0.51
    onAttach
    -0.49
    rrggbb
    -0.49
    
    -0.48
     تانيه
    -0.48
     institutional
    -0.48
    URB
    -0.48
    POSITIVE LOGITS
    dafx
    0.64
    EndContext
    0.52
    Lähteet
    0.52
     vechi
    0.51
    DataMember
    0.51
     sanitarios
    0.50
    omock
    0.49
    gameserver
    0.48
    assertAll
    0.48
     hyö
    0.48
    Activations Density 0.331%

    No Known Activations