© 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. 9417
    Prev
    Next
    INDEX
    Explanations

    the string "//" at the start of a line, XML-like tags containing the word "book", and the "m" character on a line about "harga"

    oai_token-act-pair · gemini-2.0-flash

    book

    np_max-act · gemini-2.0-flash
    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
    적으로
    -0.58
    ↵↵
    -0.57
    withstanding
    -0.56
    onsored
    -0.51
    iteness
    -0.50
     tarda
    -0.50
    }();
    -0.50
    ganu
    -0.49
    μβρίου
    -0.49
     ExecuteAsync
    -0.48
    POSITIVE LOGITS
    AddTagHelper
    0.64
    anskje
    0.64
    transQ
    0.60
    ห
    0.58
     internasional
    0.57
    PyExc
    0.57
    httphttps
    0.56
    unschweig
    0.56
     rospy
    0.56
     сме
    0.55
    Activations Density 0.404%

    No Known Activations