© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 330
    Prev
    Next
    INDEX
    Explanations

    French language, especially greetings and common words

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Esco
    -0.57
     qui
    -0.47
    ora
    -0.43
    Qui
    -0.43
     esco
    -0.42
     su
    -0.42
    via
    -0.42
     rígido
    -0.41
     McFadden
    -0.40
    un
    -0.40
    POSITIVE LOGITS
    PYX
    0.77
     ویکی‌پدی
    0.77
    клопе
    0.73
    ⓧ
    0.69
    AddTagHelper
    0.67
    ГЛА
    0.67
    TypedDataSet
    0.66
    TestingModule
    0.65
     jadx
    0.65
    pushFollow
    0.65
    Activations Density 0.724%

    No Known Activations