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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8795
    Prev
    Next
    INDEX
    Explanations

    what looks like code, especially Java's and C#'s class and method declarations and imports

    oai_token-act-pair · gemini-2.0-flash

    code access control

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     فريبيس
    -0.86
     مشين
    -0.80
    aarrggbb
    -0.80
    extAlignment
    -0.77
    :✨
    -0.75
     BoxFit
    -0.72
    LookAnd
    -0.69
     насељу
    -0.67
     nahilalakip
    -0.66
     Paglinawan
    -0.65
    POSITIVE LOGITS
    <bos>
    0.63
    private
    0.59
    ಿಯ
    0.49
    Legături
    0.48
    ждый
    0.47
     g
    0.47
    ödie
    0.47
    unknownFields
    0.47
    jam
    0.45
     Gees
    0.45
    Activations Density 0.913%

    No Known Activations