© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7988
    Prev
    Next
    INDEX
    Explanations

    the word "powers"

    oai_token-act-pair · gemini-2.0-flash

    powers

    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
    ↵
    -0.69
    he
    -0.60
    ↵↵
    -0.60
    .
    -0.60
     sáb
    -0.59
     karar
    -0.58
     apprenticeship
    -0.56
     anciennes
    -0.54
    with
    -0.54
     empowerment
    -0.54
    POSITIVE LOGITS
    ########.
    1.02
    awtextra
    0.93
     resourceCulture
    0.93
    styleType
    0.93
     snippetHide
    0.90
    etheless
    0.90
     consultato
    0.88
    )");
    0.88
     doubtnut
    0.87
    NUMX
    0.87
    Activations Density 1.394%

    No Known Activations