© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3989
    Prev
    Next
    INDEX
    Explanations

    words prefixed with "ste", as well as "-ing" words and some seemingly random activations on the words "back", "lute", "mon", and "microwave"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    +#+#
    -0.54
     Chwiliwch
    -0.54
    ANNES
    -0.53
    Tembelea
    -0.52
    過ぎて
    -0.52
    írus
    -0.52
    <_>
    -0.50
     للمعارف
    -0.49
     paroles
    -0.48
    AUD
    -0.47
    POSITIVE LOGITS
    BeginInit
    0.62
    RenderAtEndOf
    0.53
    HasForeignKey
    0.53
    CloseOperation
    0.50
     MonoBehaviour
    0.50
    basicConfig
    0.48
    ậy
    0.47
    delen
    0.47
    pping
    0.46
    instancetype
    0.45
    Activations Density 5.653%

    No Known Activations