© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8775
    Prev
    Next
    INDEX
    Explanations

    words related to seating, vehicles, and decisions

    oai_token-act-pair · gemini-2.0-flash

    chairs and sitting

    np_max-act-logits · gemini-2.0-flash

    sitting

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     sitting
    -2.61
     sit
    -2.56
     seat
    -2.52
     Sitting
    -2.42
     seats
    -2.39
    sitting
    -2.36
     seating
    -2.36
     seated
    -2.33
     Sit
    -2.31
    Sit
    -2.30
    POSITIVE LOGITS
    pyplot
    0.56
     lenker
    0.48
    HomeAsUp
    0.44
    plained
    0.43
    ់
    0.43
    PMailer
    0.42
    ői
    0.42
    Referències
    0.41
    PickerController
    0.41
     kani
    0.41
    Activations Density 2.625%

    No Known Activations