© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11660
    Prev
    Next
    INDEX
    Explanations

    words related to official authorisation, rules, and written works or their creation

    oai_token-act-pair · gemini-2.0-flash

    terms related to licensing and permits

    np_token-act-pair-logits · gpt-4o-mini

    official documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    DataAnnotations
    -0.61
     moschino
    -0.59
    Archite
    -0.58
    RegressionTest
    -0.58
    excellents
    -0.57
     betale
    -0.55
    IntoConstraints
    -0.54
    PerformLayout
    -0.54
    stdc
    -0.54
     quartzite
    -0.54
    POSITIVE LOGITS
     disponibilités
    0.57
    ிக்க
    0.53
    )_/¯
    0.51
     #"
    0.50
    Général
    0.48
     {"
    0.48
    slideUp
    0.48
    ']]
    0.47
     урна
    0.47
     Him
    0.47
    Activations Density 7.678%

    No Known Activations