© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9958
    Prev
    Next
    INDEX
    Explanations

    code-related terms like functions, processes, and protected members

    oai_token-act-pair · gemini-2.0-flash

    process

    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
    <bos>
    -0.94
     itſelf
    -0.78
    WriteTagHelper
    -0.78
     pleaſure
    -0.78
    quiries
    -0.75
     Efq
    -0.74
    PyExc
    -0.73
    ſelves
    -0.72
    selves
    -0.72
     Anſ
    -0.70
    POSITIVE LOGITS
     wikipagina
    0.59
    lojik
    0.59
    роят
    0.56
    TintMode
    0.54
     compito
    0.53
    webElementGuid
    0.52
     =
    0.52
    @
    0.52
    /***/
    0.51
    نگار
    0.51
    Activations Density 0.502%

    No Known Activations