© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14446
    Prev
    Next
    INDEX
    Explanations

    the word "ear"

    oai_token-act-pair · gemini-2.0-flash

    ear

    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
    y
    -0.83
     study
    -0.73
    ↵
    -0.71
     studying
    -0.62
     really
    -0.60
     won
    -0.57
     source
    -0.56
    <eos>
    -0.56
    .
    -0.55
    </code>
    -0.54
    POSITIVE LOGITS
    awtextra
    1.24
    AnchorStyles
    1.13
    InjectAttribute
    1.10
    parsedMessage
    1.09
    StructEnd
    1.08
    ConstraintMaker
    1.07
    styleType
    1.03
    addCriterion
    1.00
    MigrationBuilder
    1.00
     propOrder
    0.98
    Activations Density 1.868%

    No Known Activations