© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11643
    Prev
    Next
    INDEX
    Explanations

    words or short phrases which are parts of larger technical discussions, mathematical equations, coding, or other computer-related activities.

    oai_token-act-pair · gemini-2.0-flash

    code/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Theſe
    -1.06
     ſeveral
    -1.00
     nahilalakip
    -0.91
     myſelf
    -0.87
     Reſ
    -0.85
     theſe
    -0.84
     itſelf
    -0.84
     Мексичка
    -0.83
     Majefty
    -0.82
     Diſ
    -0.82
    POSITIVE LOGITS
    endphp
    0.52
    mountable
    0.52
     Réponses
    0.50
    Carriera
    0.48
     Gees
    0.48
     problemet
    0.47
    hoea
    0.47
    bigcup
    0.47
    élo
    0.46
    dius
    0.46
    Activations Density 16.853%

    No Known Activations