© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13629
    Prev
    Next
    INDEX
    Explanations

    uses of the word "what" or "that."

    oai_token-act-pair · gemini-2.0-flash

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     what
    -0.50
    what
    -0.47
    そこから
    -0.40
    שמי
    -0.40
     gestes
    -0.38
    beto
    -0.37
    GraphicsUnit
    -0.37
    option
    -0.37
     aprendido
    -0.37
     друг
    -0.36
    POSITIVE LOGITS
     Efq
    0.78
     onPostExecute
    0.74
    kloped
    0.71
     Vikipedi
    0.70
    XmlEnum
    0.70
    AtIndexPath
    0.69
     AssemblyVersion
    0.69
    +#+#
    0.66
    RegressionTest
    0.66
    ackerel
    0.66
    Activations Density 4.127%

    No Known Activations