© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15577
    Prev
    Next
    INDEX
    Explanations

    parts of JSON objects

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms and symbols

    np_token-act-pair-logits · gpt-4o-mini

    Code/programming context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Saint
    -0.50
     u
    -0.49
    ology
    -0.49
     modern
    -0.45
     subject
    -0.45
     point
    -0.44
     Y
    -0.43
    alee
    -0.43
     history
    -0.43
     U
    -0.43
    POSITIVE LOGITS
    +#+#
    0.84
     MainAxisSize
    0.75
     Drapeau
    0.72
    ContentAsync
    0.71
    Hentet
    0.68
    :+:
    0.66
     AssemblyCompany
    0.66
    хьтан
    0.65
     تضيفلها
    0.64
     Factbook
    0.64
    Activations Density 0.777%

    No Known Activations