© 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. 266
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages, often in scientific or technical contexts

    oai_token-act-pair · gemini-2.0-flash

    Dates and Numerical Data

    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
     Rodgers
    -0.52
     absch
    -0.49
    URLException
    -0.49
    Controllo
    -0.48
    haft
    -0.48
    ticelli
    -0.48
    ಾರ
    -0.47
     AssemblyTitle
    -0.47
     اطلع
    -0.47
     rist
    -0.47
    POSITIVE LOGITS
     Pliny
    0.56
     kasarigan
    0.53
     Familienname
    0.48
    astrar
    0.48
     Plin
    0.48
     noDo
    0.47
    abestanden
    0.46
     quæ
    0.46
    akuza
    0.46
    esez
    0.45
    Activations Density 1.392%

    No Known Activations