© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9551
    Prev
    Next
    INDEX
    Explanations

    technical language used in scientific journal articles

    oai_token-act-pair · gemini-2.0-flash

    technical or programming terminology

    np_token-act-pair-logits · gpt-4o-mini

    academic text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    atguigu
    -0.64
    chtenstein
    -0.62
    makeText
    -0.59
    andowski
    -0.56
    tetur
    -0.53
    ích
    -0.52
    jonal
    -0.50
    ADUATE
    -0.48
    etan
    -0.48
     mismos
    -0.47
    POSITIVE LOGITS
    uxxxx
    0.71
    ValueStyle
    0.66
     يتيمه
    0.61
    DeleteBehavior
    0.61
     pleaſure
    0.59
     myſelf
    0.56
     resourceCulture
    0.56
    Viitteet
    0.55
     createSlice
    0.55
    ſelf
    0.54
    Activations Density 4.496%

    No Known Activations