© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12358
    Prev
    Next
    INDEX
    Explanations

    the adjective "little" near words suggesting small or incremental change

    oai_token-act-pair · gemini-2.0-flash

    little

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     little
    -2.59
    little
    -2.41
    Little
    -2.30
     Little
    -2.17
     LITTLE
    -2.05
    LITTLE
    -1.81
     lil
    -1.27
    <bos>
    -1.15
     poco
    -1.09
     wenig
    -1.04
    POSITIVE LOGITS
    kháu
    0.52
     razon
    0.48
    úblico
    0.47
    xaml
    0.47
     Offshore
    0.46
     tạm
    0.46
     ErrIntOverflow
    0.45
    printLine
    0.45
    AutoScale
    0.45
    новништво
    0.44
    Activations Density 3.570%

    No Known Activations