© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10992
    Prev
    Next
    INDEX
    Explanations

    a mixture of Malay and English words, particularly focusing on pronouns, discounts, and personal experiences.

    oai_token-act-pair · gemini-2.0-flash

    dis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ImageContext
    -0.90
    ValueStyle
    -0.90
    TargetException
    -0.83
    RenderAtEndOf
    -0.81
    Tikang
    -0.81
     BoxFit
    -0.77
     dunes
    -0.76
    ruptedException
    -0.75
    verwijspagina
    -0.73
    uxxxx
    -0.73
    POSITIVE LOGITS
     by
    0.63
     pe
    0.48
     super
    0.48
    pushButton
    0.47
     mit
    0.47
    ))/
    0.47
     sem
    0.46
     pela
    0.46
     توسط
    0.46
    memoized
    0.45
    Activations Density 0.573%

    No Known Activations