© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15732
    Prev
    Next
    INDEX
    Explanations

    words with the suffix 'ci' followed by a vowel

    oai_token-act-pair · gemini-2.0-flash

    ending in "cy"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     متعلقه
    -1.00
    bootstrapcdn
    -1.00
     שוליים
    -0.85
     autorytatywna
    -0.82
    GEBURTSDATUM
    -0.82
    Попис
    -0.77
    +:+
    -0.77
    iastes
    -0.76
     виправивши
    -0.75
     للمعارف
    -0.75
    POSITIVE LOGITS
    cy
    0.84
    acy
    0.80
    ACY
    0.68
    icy
    0.62
    ecy
    0.60
    AC
    0.59
    acies
    0.56
    ency
    0.55
    Cy
    0.55
    cies
    0.54
    Activations Density 0.929%

    No Known Activations