© 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. 12891
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to illness or feeling unwell.

    oai_token-act-pair · gemini-2.0-flash

    sickness

    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
     un
    -0.43
     let
    -0.43
    readAs
    -0.42
    Portály
    -0.41
    PerformLayout
    -0.41
    heizung
    -0.41
     Италијани
    -0.40
     Z
    -0.40
    انيف
    -0.40
     across
    -0.39
    POSITIVE LOGITS
     dizzy
    0.94
     dizziness
    0.84
     vestibular
    0.79
     fainting
    0.79
    TestingModule
    0.73
     Dizziness
    0.73
    #+#
    0.73
     vertigo
    0.72
     concussion
    0.68
     fainted
    0.66
    Activations Density 1.381%

    No Known Activations