© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12509
    Prev
    Next
    INDEX
    Explanations

    the <p>, <i>, and <b> tags in HTML

    oai_token-act-pair · gemini-2.0-flash

    HTML italic tag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Efe
    -0.64
    aderie
    -0.60
    PYX
    -0.59
    LinkId
    -0.58
    पन
    -0.57
     нат
    -0.57
     canadensis
    -0.56
     africana
    -0.56
     kant
    -0.55
     asiatique
    -0.54
    POSITIVE LOGITS
    TagMode
    0.77
    saraba
    0.66
     facie
    0.59
     FetchType
    0.58
    ;#
    0.56
    APORE
    0.56
    BeginContext
    0.55
    ponses
    0.54
    WaitGroup
    0.54
     Normdatei
    0.54
    Activations Density 4.606%

    No Known Activations