© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12131
    Prev
    Next
    INDEX
    Explanations

    quotes about people, especially celebrities, speaking or being mentioned in the news

    oai_token-act-pair · gemini-2.0-flash

    someone is saying something

    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
     дописавши
    -0.84
    MessageTagHelper
    -0.84
    IUrlHelper
    -0.75
     kasarigan
    -0.75
     NSCoder
    -0.70
    Искәрмәләр
    -0.68
    yntaxException
    -0.68
    المناصب
    -0.68
    IntoConstraints
    -0.68
     StatefulWidget
    -0.67
    POSITIVE LOGITS
     dead
    0.44
     szóci
    0.36
     asesinado
    0.36
    matter
    0.35
    dead
    0.35
     servicios
    0.34
    ríguez
    0.34
     disfraces
    0.34
     morts
    0.32
    ("")]
    0.32
    Activations Density 0.927%

    No Known Activations