© 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. 12881
    Prev
    Next
    INDEX
    Explanations

    terms referring to stools, chairs, and toilets

    oai_token-act-pair · gemini-2.0-flash

    chairs, stools, stool exams

    np_max-act · gemini-2.0-flash

    chairs

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    tableFuture
    -0.67
    ázaro
    -0.65
    ruptedException
    -0.62
    riwal
    -0.60
     consciences
    -0.59
     whistled
    -0.58
    addCriterion
    -0.58
    wpi
    -0.57
    HostException
    -0.57
     whistles
    -0.57
    POSITIVE LOGITS
     seat
    0.79
     seats
    0.74
    Seats
    0.66
     Seats
    0.66
     chair
    0.64
    Seat
    0.63
     kursi
    0.63
    kursi
    0.63
    seats
    0.62
     chairs
    0.62
    Activations Density 0.447%

    No Known Activations