© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8284
    Prev
    Next
    INDEX
    Explanations

    code snippets, configuration settings, and attributes, especially concerning XML and Angular models

    oai_token-act-pair · gemini-2.0-flash

    computer code and configuration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     useless
    -0.86
     pointless
    -0.86
    useless
    -0.77
    Useless
    -0.76
     meaningless
    -0.67
     usefulness
    -0.66
     purpose
    -0.65
     point
    -0.65
     смы
    -0.65
    意义
    -0.63
    POSITIVE LOGITS
     виправивши
    0.75
    verifyException
    0.70
     utafitiHapana
    0.61
    ="@+
    0.60
     estekak
    0.60
    OGND
    0.59
    DoubleQuotes
    0.57
    __*/
    0.57
    anInt
    0.57
     jugé
    0.56
    Activations Density 1.864%

    No Known Activations