© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6160
    Prev
    Next
    INDEX
    Explanations

    content in a non-English language

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    PerformLayout
    -0.52
    But
    -0.51
    Located
    -0.50
    :✨
    -0.50
    帖最后由
    -0.49
    WebElementEntity
    -0.45
     But
    -0.44
    Later
    -0.43
     With
    -0.42
    Referanser
    -0.42
    POSITIVE LOGITS
     Cassie
    0.62
     numerals
    0.57
     Lucille
    0.56
     Bunt
    0.55
     Terence
    0.54
     Aene
    0.52
     Zeke
    0.52
     Pind
    0.50
     Interchange
    0.50
     Astrid
    0.50
    Activations Density 2.974%

    No Known Activations