© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8510
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the," particularly within phrases indicating connection or display.

    oai_token-act-pair · gemini-2.0-flash

    roads

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ตก
    -0.50
     éco
    -0.49
    ficação
    -0.48
     uintptr
    -0.48
     bản
    -0.48
    ctum
    -0.47
    ESIS
    -0.47
     tắt
    -0.46
    Фа
    -0.46
    initas
    -0.46
    POSITIVE LOGITS
     road
    1.17
    road
    0.89
    Road
    0.85
     roads
    0.84
     Road
    0.81
     ROAD
    0.79
     skies
    0.71
     carretera
    0.70
     jalan
    0.69
     air
    0.68
    Activations Density 0.803%

    No Known Activations