© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1430
    Prev
    Next
    INDEX
    Explanations

    words associated with inventions and technology, especially lighting

    oai_token-act-pair · gemini-2.0-flash

    light, lamps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Licht
    -0.47
    Lights
    -0.47
     caseros
    -0.46
    려
    -0.45
    Light
    -0.44
     casero
    -0.44
     doméstico
    -0.44
     SwitchCompat
    -0.44
    lights
    -0.43
    onOptions
    -0.43
    POSITIVE LOGITS
    RenderAtEndOf
    0.68
    iocene
    0.62
    persky
    0.57
    contentLoaded
    0.56
    ########.
    0.56
    ]--;
    0.56
     sumpay
    0.55
     لينك
    0.54
    %")
    0.54
    ucchini
    0.54
    Activations Density 38.556%

    No Known Activations