© 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. 3965
    Prev
    Next
    INDEX
    Explanations

    words about buying GPS equipment for business use

    oai_token-act-pair · gemini-2.0-flash

    text fragments

    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
    ocats
    -0.47
    rhosis
    -0.46
    GroupLayout
    -0.46
    uticos
    -0.46
     reta
    -0.45
     Diener
    -0.45
    odils
    -0.44
     osa
    -0.44
     expédié
    -0.44
    rys
    -0.43
    POSITIVE LOGITS
     Савезне
    0.68
    Datuak
    0.66
    nonatomic
    0.64
    AxisAlignment
    0.64
    WebVitals
    0.61
     typelib
    0.59
     StatelessWidget
    0.59
    ChildScrollView
    0.58
    انيف
    0.57
     surla
    0.56
    Activations Density 2.673%

    No Known Activations