© 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. 2028
    Prev
    Next
    INDEX
    Explanations

    words relating to business, taxes, and dates, as well as the Getty image hosting service

    oai_token-act-pair · gemini-2.0-flash

    news/article excerpts

    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
     New
    -0.65
     Riproduzione
    -0.51
     ExecuteAsync
    -0.50
    New
    -0.49
     Económica
    -0.49
     Arque
    -0.47
     Nuevas
    -0.46
     Jurí
    -0.46
     Condiciones
    -0.43
     contemporanea
    -0.43
    POSITIVE LOGITS
    ">—
    0.69
    ">//
    0.69
     ».
    0.65
     »
    0.61
    /***/
    0.60
     <<
    0.60
    __.__
    0.60
    :"-"`
    0.59
     onCreateView
    0.59
    __:
    0.59
    Activations Density 7.879%

    No Known Activations