© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7994
    Prev
    Next
    INDEX
    Explanations

    technical terms related to car transmissions and mechanics

    oai_token-act-pair · gemini-2.0-flash

    transmission

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ⓧ
    -0.88
    IntoConstraints
    -0.86
     kasarigan
    -0.85
    NameInMap
    -0.84
    Jeografia
    -0.79
    rungsseite
    -0.78
    DockStyle
    -0.76
    hoeddwyd
    -0.76
     дописавши
    -0.73
    Autoritní
    -0.72
    POSITIVE LOGITS
     Auto
    0.78
    Auto
    0.76
     auto
    0.73
     Chevrolet
    0.64
    auto
    0.61
     Volkswagen
    0.60
     AUTO
    0.59
     Peugeot
    0.59
    Volkswagen
    0.58
     Toyota
    0.57
    Activations Density 1.426%

    No Known Activations