© 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. 3308
    Prev
    Next
    INDEX
    Explanations

    the phrase "well known"

    oai_token-act-pair · gemini-2.0-flash

    known

    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
    #
    -0.68
     ddelweddau
    -0.68
    GenerationType
    -0.65
     OFDb
    -0.62
    WebServlet
    -0.62
    Assured
    -0.61
    yship
    -0.61
     papyrus
    -0.60
    }^{+\
    -0.60
    saurus
    -0.58
    POSITIVE LOGITS
     الحره
    0.66
     utilisons
    0.59
    ագրություններ
    0.59
    ExecutorService
    0.55
    IsContent
    0.54
    fjspx
    0.54
    有名な
    0.54
     today
    0.52
    findpost
    0.52
    asgi
    0.52
    Activations Density 0.282%

    No Known Activations