© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13049
    Prev
    Next
    INDEX
    Explanations

    terms being legally defined, or otherwise medically classified

    oai_token-act-pair · gemini-2.0-flash

    defined

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    RenderAtEndOf
    -0.66
     {}'.
    -0.65
    umą
    -0.62
     broad
    -0.61
    ter
    -0.59
     large
    -0.59
     fine
    -0.59
    ton
    -0.58
     newer
    -0.58
     @"/
    -0.57
    POSITIVE LOGITS
     StatefulWidget
    0.96
    ertale
    0.84
     StatelessWidget
    0.83
    urtstag
    0.83
    ymce
    0.79
    ésor
    0.79
    elesai
    0.78
    +#+#
    0.78
    leyball
    0.78
     sanguí
    0.78
    Activations Density 2.190%

    No Known Activations