© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12267
    Prev
    Next
    INDEX
    Explanations

    questions about who did something or how something will happen

    oai_token-act-pair · gemini-2.0-flash

    whom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    transQ
    -0.58
     en
    -0.48
     o
    -0.45
     n
    -0.42
     האח
    -0.42
    ėjimas
    -0.41
     '
    -0.40
    {'
    -0.40
     for
    -0.40
     N
    -0.40
    POSITIVE LOGITS
    NOPQRST
    0.88
     فريبيس
    0.88
     utafitiHapana
    0.87
    PerformLayout
    0.83
    AsUp
    0.80
     Italijani
    0.76
     Wiktionnaire
    0.76
     Jefus
    0.76
     ―――――
    0.76
    migrationBuilder
    0.75
    Activations Density 1.484%

    No Known Activations