© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15887
    Prev
    Next
    INDEX
    Explanations

    phrases describing taking action, especially increasing something

    oai_token-act-pair · gemini-2.0-flash

    their

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ContentAsync
    -0.79
    StoryboardSegue
    -0.62
     Насе
    -0.61
     schist
    -0.56
     honour
    -0.56
     Havel
    -0.55
    +:+
    -0.54
    /*
    -0.54
     parentage
    -0.54
     pah
    -0.52
    POSITIVE LOGITS
     Intens
    0.59
     yoğun
    0.58
     Intensi
    0.57
    EDEFAULT
    0.57
     интенсив
    0.56
     soutenu
    0.56
     intensi
    0.54
    Filmografie
    0.54
     Efforts
    0.54
     efforts
    0.54
    Activations Density 1.561%

    No Known Activations