© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8079
    Prev
    Next
    INDEX
    Explanations

    the prefixes "radio" and "macro"

    oai_token-act-pair · gemini-2.0-flash

    ror

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    AsUp
    -0.78
     Monfieur
    -0.75
     متعلقه
    -0.73
    RTDA
    -0.73
     myſelf
    -0.73
     الرياضيه
    -0.70
     Majefty
    -0.70
    IntoConstraints
    -0.70
    HomeAsUpEnabled
    -0.70
    المناصب
    -0.69
    POSITIVE LOGITS
     mark
    0.92
     macro
    0.85
     MARK
    0.82
     Mark
    0.81
    macro
    0.79
     Macro
    0.76
    MARK
    0.75
    Mark
    0.73
     marking
    0.73
    mark
    0.72
    Activations Density 0.599%

    No Known Activations